{"results":[{"id":"doaj_10.1016/j.csite.2024.105555","title":"Experimental and numerical study on cavitation flow characteristics of refrigerants with different thermophysical properties in confined micro-clearance","authors":[{"name":"Shaohang Yan"},{"name":"Tianwei Lai"},{"name":"Zhen Wang"},{"name":"Qi Zhao"},{"name":"Yu Hou"}],"abstract":"In high-speed hydraulic machinery, its efficiency and reliability are affected by the cavitation in the bearing. Due to the confined effect of the bearing clearance, cavitation bubbles grow in a two-dimensional way. To uncover the cavitation process with confined and high speed shearing effect, the high-speed cavitation flowing of different refrigerants is researched experimentally based on the high-speed shearing test rig with micro-clearance. The influence of thermophysical properties on growth of cavitation bubble is evaluated and analyzed. The confined effect of micro-clearance and high-speed shearing effect has a significant influence on the cavitation bubbles evolution. The high-speed camera is used to record the morphology of cavitation bubbles for various refrigerants with different thermalphysical properties. Furthermore, the thermal-sensitive cavitation model is used to analyze the bubble-foam alternation from cavitation flow inside micro-clearance. For different refrigerants, the growth process of cavitation bubble area is exponential. Inside the micro-clearance, the cavitation inducing pressure drops of different refrigerants are analogous due to the similar thermodynamic properties. According to pressure drop during cavitation, different refrigerants are classified by introducing dimensionless numbers, σ·Re (Jie et al., 2009) [2] and σ·We. The pressure and temperature drop increase with the dimensionless numbers. The refrigerants with similar thermodynamic properties have a similar relationship between dimensionless number and supercooling degree.","source":"DOAJ","year":2025,"language":"","subjects":["Engineering (General). Civil engineering (General)"],"doi":"10.1016/j.csite.2024.105555","url":"http://www.sciencedirect.com/science/article/pii/S2214157X24015867","is_open_access":true,"published_at":"","score":69},{"id":"doaj_10.14746/i.2025.39.48.9","title":"Dysonans ludonarracyjny w światocentrycznych grach wideo","authors":[{"name":"Michał Mróz"}],"abstract":"\nThe author explores the issue of “ludonarrative dissonance”, a term developed by the game designer C. Hocking in his critique of the game BioShock. The author explains Hocking’s arguments and then expands on the term, disagreeing with Hocking. In the case of BioShock, the author interprets the dissonance not as a design flaw but as a deliberate narrative strategy that momentarily distances the player from the game’s fiction to emphasize its metanarrative dimension. The author argues that ludonarrative dissonance is itself part of videogame poetics, thus echoing the works of F. Seraphine and P. Grabarczyk \u0026 B.W. Kampmann. The author then examines how ludonarrative dissonance may appear in vast, nonlinear open-world cRPGs. An analysis of examples from The Elder Scrolls: Skyrim, Fallout 3, and Fallout 4 reveals various instances of unintended dissonance. Finally, the author compares these games to Fallout: New Vegas, presenting it as an example of harmonizing the narrative – the main motifs and story – with the narrativity of gameplay, including rules, mechanics, and vast player agency.\n","source":"DOAJ","year":2025,"language":"","subjects":["Photography","Dramatic representation. The theater"],"doi":"10.14746/i.2025.39.48.9","url":"https://pressto.amu.edu.pl/index.php/i/article/view/51255","is_open_access":true,"published_at":"","score":69},{"id":"arxiv_2501.06216","title":"Understanding colors of Dufaycolor: Can we recover them using historical colorimetric and spectral data?","authors":[{"name":"Jan Hubička"},{"name":"Linda Kimrová"},{"name":"Melichar Konečný"}],"abstract":"Dufaycolor, an additive color photography process produced from 1935 to the late 1950s, represents one of the most advanced iterations of this technique. This paper presents ongoing research and development of an open-source Color-Screen tool designed to reconstruct the original colors of additive color photographs. We discuss the incorporation of historical measurements of dyes used in the production of the color-screen filter (réseau) to achieve accurate color recovery.","source":"arXiv","year":2025,"language":"en","subjects":["cs.CV","cs.GR"],"doi":"10.23738/RCASB.013","url":"https://arxiv.org/abs/2501.06216","pdf_url":"https://arxiv.org/pdf/2501.06216","is_open_access":true,"published_at":"2025-01-05T13:38:47Z","score":69},{"id":"arxiv_2502.02596","title":"The photography transforms and their analytic inversion formulas","authors":[{"name":"Duo Liu"},{"name":"Gangrong Qu"},{"name":"Shan Gao"}],"abstract":"The light field reconstruction from the focal stack can be mathematically formulated as an ill-posed integral equation inversion problem. Although the previous research about this problem has made progress both in practice and theory, its forward problem and inversion in a general form still need to be studied. In this paper, to model the forward problem rigorously, we propose three types of photography transforms with different integral geometry characteristics that extend the forward operator to the arbitrary $n$-dimensional case. We prove that these photography transforms are equivalent to the Radon transform with the coupling relation between variables. We also obtain some properties of the photography transforms, including the Fourier slice theorem, the convolution theorem, and the convolution property of the dual operator, which are very similar to those of the classic Radon transform. Furthermore, the representation of the normal operator and the analytic inversion formula for the photography transforms are derived and they are quite different from those of the classic Radon transform.","source":"arXiv","year":2025,"language":"en","subjects":["math.FA","math-ph"],"url":"https://arxiv.org/abs/2502.02596","pdf_url":"https://arxiv.org/pdf/2502.02596","is_open_access":true,"published_at":"2025-01-14T04:12:40Z","score":69},{"id":"arxiv_2504.10090","title":"CameraBench: Benchmarking Visual Reasoning in MLLMs via Photography","authors":[{"name":"I-Sheng Fang"},{"name":"Jun-Cheng Chen"}],"abstract":"Large language models (LLMs) and multimodal large language models (MLLMs) have significantly advanced artificial intelligence. However, visual reasoning, reasoning involving both visual and textual inputs, remains underexplored. Recent advancements, including the reasoning models like OpenAI o1 and Gemini 2.0 Flash Thinking, which incorporate image inputs, have opened this capability. In this ongoing work, we focus specifically on photography-related tasks because a photo is a visual snapshot of the physical world where the underlying physics (i.e., illumination, blur extent, etc.) interplay with the camera parameters. Successfully reasoning from the visual information of a photo to identify these numerical camera settings requires the MLLMs to have a deeper understanding of the underlying physics for precise visual comprehension, representing a challenging and intelligent capability essential for practical applications like photography assistant agents. We aim to evaluate MLLMs on their ability to distinguish visual differences related to numerical camera settings, extending a methodology previously proposed for vision-language models (VLMs). Our preliminary results demonstrate the importance of visual reasoning in photography-related tasks. Moreover, these results show that no single MLLM consistently dominates across all evaluation tasks, demonstrating ongoing challenges and opportunities in developing MLLMs with better visual reasoning.","source":"arXiv","year":2025,"language":"en","subjects":["cs.CV","cs.CL"],"url":"https://arxiv.org/abs/2504.10090","pdf_url":"https://arxiv.org/pdf/2504.10090","is_open_access":true,"published_at":"2025-04-14T10:53:44Z","score":69},{"id":"arxiv_2505.19065","title":"MMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment Database","authors":[{"name":"Jiashuo Chang"},{"name":"Zhengyi Li"},{"name":"Jianxun Lou"},{"name":"Zhen Qiu"},{"name":"Hanhe Lin"}],"abstract":"Macro photography (MP) is a specialized field of photography that captures objects at an extremely close range, revealing tiny details. Although an accurate macro photography image quality assessment (MPIQA) metric can benefit macro photograph capturing, which is vital in some domains such as scientific research and medical applications, the lack of MPIQA data limits the development of MPIQA metrics. To address this limitation, we conducted a large-scale MPIQA study. Specifically, to ensure diversity both in content and quality, we sampled 2,000 MP images from 15,700 MP images, collected from three public image websites. For each MP image, 17 (out of 21 after outlier removal) quality ratings and a detailed quality report of distortion magnitudes, types, and positions are gathered by a lab study. The images, quality ratings, and quality reports form our novel multi-labeled MPIQA database, MMP-2k. Experimental results showed that the state-of-the-art generic IQA metrics underperform on MP images. The database and supplementary materials are available at https://github.com/Future-IQA/MMP-2k.","source":"arXiv","year":2025,"language":"en","subjects":["cs.CV"],"doi":"10.1109/ICIP55913.2025.11084596","url":"https://arxiv.org/abs/2505.19065","pdf_url":"https://arxiv.org/pdf/2505.19065","is_open_access":true,"published_at":"2025-05-25T09:47:10Z","score":69},{"id":"arxiv_2501.06448","title":"Discovering an Image-Adaptive Coordinate System for Photography Processing","authors":[{"name":"Ziteng Cui"},{"name":"Lin Gu"},{"name":"Tatsuya Harada"}],"abstract":"Curve \u0026 Lookup Table (LUT) based methods directly map a pixel to the target output, making them highly efficient tools for real-time photography processing. However, due to extreme memory complexity to learn full RGB space mapping, existing methods either sample a discretized 3D lattice to build a 3D LUT or decompose into three separate curves (1D LUTs) on the RGB channels. Here, we propose a novel algorithm, IAC, to learn an image-adaptive Cartesian coordinate system in the RGB color space before performing curve operations. This end-to-end trainable approach enables us to efficiently adjust images with a jointly learned image-adaptive coordinate system and curves. Experimental results demonstrate that this simple strategy achieves state-of-the-art (SOTA) performance in various photography processing tasks, including photo retouching, exposure correction, and white-balance editing, while also maintaining a lightweight design and fast inference speed.","source":"arXiv","year":2025,"language":"en","subjects":["cs.CV"],"url":"https://arxiv.org/abs/2501.06448","pdf_url":"https://arxiv.org/pdf/2501.06448","is_open_access":true,"published_at":"2025-01-11T06:20:07Z","score":69},{"id":"doaj_10.38140/as.v31i2.8398","title":"City beautification through corporate social responsibility landscape branding in enhancing urban landscape identity in Kisumu City, Kenya","authors":[{"name":"Edwin Koyoo "}],"abstract":"City identity and branding have traditionally been shaped by iconic architecture, including monumental buildings and landmarks. However, recent studies have begun to explore city branding through corporate social responsibility (CSR) initiatives, particularly from a landscape perspective. There is limited research, particularly in the Global South, examining the role of CSR in the enhancement of open green spaces and its contribution to shaping urban landscape identity. This study investigates CSR-driven beautification projects in Kisumu City, Kenya, where corporate-funded initiatives have sought to improve urban landscapes through the landscaping of road islands and roundabouts, alongside broader urban renewal efforts. The article aims to document the spatial attributes of these CSR projects; assess their current status in terms of cleanliness, safety, and maintenance, as well as identify the challenges faced in implementing CSR-driven beautification efforts. The aim of these projects is not only to promote the city’s unique urban identity, but also to enhance the corporate image through landscape branding. A qualitative research methodology is employed, involving field observations, GIS mapping, and photography, complemented by purposive interviews. The findings reveal not only diverse landscape designs, including water features and sculptures, but also highlight significant issues with upkeep, safety concerns from street urchins, and the overall deterioration of some sites. These results are valuable for policymakers in city governments and corporations involved in CSR projects, offering insights into how such initiatives can better contribute to urban landscape identity, city branding, and the sustainability of urban beautification efforts.","source":"DOAJ","year":2024,"language":"","subjects":["Building construction"],"doi":"10.38140/as.v31i2.8398","url":"https://journals.ufs.ac.za/index.php/as/article/view/8398","is_open_access":true,"published_at":"","score":68},{"id":"doaj_10.1049/ipr2.13287","title":"A comprehensive construction of deep neural network‐based encoder–decoder framework for automatic image captioning systems","authors":[{"name":"Md Mijanur Rahman"},{"name":"Ashik Uzzaman"},{"name":"Sadia Islam Sami"},{"name":"Fatema Khatun"},{"name":"Md Al‐Amin Bhuiyan"}],"abstract":"Abstract This study introduces a novel encoder–decoder framework based on deep neural networks and provides a thorough investigation into the field of automatic picture captioning systems. The suggested model uses a “long short‐term memory” decoder for word prediction and sentence construction, and a “convolutional neural network” as an encoder that is skilled at object recognition and spatial information retention. The long short‐term memory network functions as a sequence processor, generating a fixed‐length output vector for final predictions, while the VGG‐19 model is utilized as an image feature extractor. For both training and testing, the study uses a variety of photos from open‐access datasets, such as Flickr8k, Flickr30k, and MS COCO. The Python platform is used for implementation, with Keras and TensorFlow as backends. The experimental findings, which were assessed using the “bilingual evaluation understudy” metric, demonstrate the effectiveness of the suggested methodology in automatically captioning images. By addressing spatial relationships in images and producing logical, contextually relevant captions, the paper advances image captioning technology. Insightful ideas for future study directions are generated by the discussion of the difficulties faced during the experimentation phase. By establishing a strong neural network architecture for automatic picture captioning, this study creates opportunities for future advancement and improvement in the area.","source":"DOAJ","year":2024,"language":"","subjects":["Photography","Computer software"],"doi":"10.1049/ipr2.13287","url":"https://doi.org/10.1049/ipr2.13287","is_open_access":true,"published_at":"","score":68},{"id":"doaj_10.1016/j.jrmge.2023.07.025","title":"Effect of drying cracks on swelling and self-healing of bentonite-sand blocks used as engineered barriers for radioactive waste disposal","authors":[{"name":"Yu Tan"},{"name":"Guangping Zhou"},{"name":"Huyuan Zhang"},{"name":"Xiaoya Li"},{"name":"Ping Liu"}],"abstract":"Experiments were conducted to evaluate the healing of drying cracks in air-dried bentonite-sand blocks after hydration and swelling in groundwater, providing justifications to simplify the protection of blocks prior to installation in a high-level radioactive waste repository. Synthetic groundwater was prepared to represent the geochemistry of Beishan groundwater, and was used to hydrate the blocks during the swelling pressure and swelling strain measurements, as Beishan is the most promising site for China's repository. Healing of the surface cracks was recorded by photography, and healing of the internal cracks was visualized by CT images and hydraulic conductivity of air-dried blocks. The results indicate that the maximum swelling pressure and swelling strain are primarily affected by the geochemistry of Beishan groundwater, but not affected by the drying cracks. The maximum swelling pressure and swelling strain of air-dried blocks are comparable to or even higher than the pressure and strain of fresh blocks. The maximum swelling pressure measured in strong (i.e. high ion strength) Beishan groundwater was 44% of the pressure measured in deionized (DI) water, and the maximum swelling strain was reduced to 23% of the strain measured in DI water. Nevertheless, the remained swelling of the blocks hydrated in strong Beishan groundwater was sufficient to heal the surface and internal drying cracks, as demonstrated by the pictures of surface cracks and CT images. The hydraulic conductivity of the air-dried block permeated with strong groundwater was comparable (3.7× higher) to the hydraulic conductivity of the fresh block, indicating the self-healing of drying cracks after hydration and swelling in groundwater. A simplified method of protecting the block with plastic wraps before installation is recommended, since the remained swelling of the block hydrated in Beishan groundwater is sufficient to heal the drying cracks.","source":"DOAJ","year":2024,"language":"","subjects":["Engineering geology. Rock mechanics. Soil mechanics. Underground construction"],"doi":"10.1016/j.jrmge.2023.07.025","url":"http://www.sciencedirect.com/science/article/pii/S167477552300330X","is_open_access":true,"published_at":"","score":68},{"id":"arxiv_2405.05422","title":"EarthMatch: Iterative Coregistration for Fine-grained Localization of Astronaut Photography","authors":[{"name":"Gabriele Berton"},{"name":"Gabriele Goletto"},{"name":"Gabriele Trivigno"},{"name":"Alex Stoken"},{"name":"Barbara Caputo"},{"name":"Carlo Masone"}],"abstract":"Precise, pixel-wise geolocalization of astronaut photography is critical to unlocking the potential of this unique type of remotely sensed Earth data, particularly for its use in disaster management and climate change research. Recent works have established the Astronaut Photography Localization task, but have either proved too costly for mass deployment or generated too coarse a localization. Thus, we present EarthMatch, an iterative homography estimation method that produces fine-grained localization of astronaut photographs while maintaining an emphasis on speed. We refocus the astronaut photography benchmark, AIMS, on the geolocalization task itself, and prove our method's efficacy on this dataset. In addition, we offer a new, fair method for image matcher comparison, and an extensive evaluation of different matching models within our localization pipeline. Our method will enable fast and accurate localization of the 4.5 million and growing collection of astronaut photography of Earth. Webpage with code and data at https://earthloc-and-earthmatch.github.io","source":"arXiv","year":2024,"language":"en","subjects":["cs.CV"],"url":"https://arxiv.org/abs/2405.05422","pdf_url":"https://arxiv.org/pdf/2405.05422","is_open_access":true,"published_at":"2024-05-08T20:46:36Z","score":68},{"id":"arxiv_2406.13007","title":"NTIRE 2024 Challenge on Night Photography Rendering","authors":[{"name":"Egor Ershov"},{"name":"Artyom Panshin"},{"name":"Oleg Karasev"},{"name":"Sergey Korchagin"},{"name":"Shepelev Lev"},{"name":"Alexandr Startsev"},{"name":"Daniil Vladimirov"},{"name":"Ekaterina Zaychenkova"},{"name":"Nikola Banić"},{"name":"Dmitrii Iarchuk"},{"name":"Maria Efimova"},{"name":"Radu Timofte"},{"name":"Arseniy Terekhin"},{"name":"Shuwei Yue"},{"name":"Yuyang Liu"},{"name":"Minchen Wei"},{"name":"Lu Xu"},{"name":"Chao Zhang"},{"name":"Yasi Wang"},{"name":"Furkan Kınlı"},{"name":"Doğa Yılmaz"},{"name":"Barış Özcan"},{"name":"Furkan Kıraç"},{"name":"Shuai Liu"},{"name":"Jingyuan Xiao"},{"name":"Chaoyu Feng"},{"name":"Hao Wang"},{"name":"Guangqi Shao"},{"name":"Yuqian Zhang"},{"name":"Yibin Huang"},{"name":"Wei Luo"},{"name":"Liming Wang"},{"name":"Xiaotao Wang"},{"name":"Lei Lei"},{"name":"Simone Zini"},{"name":"Claudio Rota"},{"name":"Marco Buzzelli"},{"name":"Simone Bianco"},{"name":"Raimondo Schettini"},{"name":"Jin Guo"},{"name":"Tianli Liu"},{"name":"Mohao Wu"},{"name":"Ben Shao"},{"name":"Qirui Yang"},{"name":"Xianghui Li"},{"name":"Qihua Cheng"},{"name":"Fangpu Zhang"},{"name":"Zhiqiang Xu"},{"name":"Jingyu Yang"},{"name":"Huanjing Yue"}],"abstract":"This paper presents a review of the NTIRE 2024 challenge on night photography rendering. The goal of the challenge was to find solutions that process raw camera images taken in nighttime conditions, and thereby produce a photo-quality output images in the standard RGB (sRGB) space. Unlike the previous year's competition, the challenge images were collected with a mobile phone and the speed of algorithms was also measured alongside the quality of their output. To evaluate the results, a sufficient number of viewers were asked to assess the visual quality of the proposed solutions, considering the subjective nature of the task. There were 2 nominations: quality and efficiency. Top 5 solutions in terms of output quality were sorted by evaluation time (see Fig. 1). The top ranking participants' solutions effectively represent the state-of-the-art in nighttime photography rendering. More results can be found at https://nightimaging.org.","source":"arXiv","year":2024,"language":"en","subjects":["cs.CV"],"url":"https://arxiv.org/abs/2406.13007","pdf_url":"https://arxiv.org/pdf/2406.13007","is_open_access":true,"published_at":"2024-06-18T18:56:25Z","score":68},{"id":"doaj_10.22394/2412-9410-2023-9-4-268-285","title":"Fantasies of being somebody: Auto / biographic potential of posing conventions","authors":[{"name":"K. O. Gusarova"}],"abstract":"The article examines the tension between the individual and the collective in current mainstream photographic practice, which is considered within the long-term historical context of commercial portraiture. The individualizing tendencies of this representational tradition as well as its status as (auto)biographical fiction were astutely analyzed by the Russian avant-garde thinkers Alexander Rodchenko and Osip Brik. Criticizing the persistence of “painterly” clichés in studio photography of their time, they saw these conventional elements as something that obscures and distorts reality, substituting for it a beautiful picture. For these leftist theorists, reality was primarily defined by the interplay of social forces, and isolating the subject within the picture frame was sufficient grounds for their disapproval. Taking up their notion of cliché applied particularly to posing, this article proposes to view it, instead, as an entry point into the usually invisible collective dimension of each individual portrait. The first section of the article discusses historical precedents to current mainstream photographic portraiture in terms of class- and gender-specific pressures on the sitters which have contributed to the homogenization of the genre’s visual canon. The suggestion to view stylistically similar images of individuals as expressing a latent collectivity is developed in the second part of the article, which analyzes Jana Romanova’s photographic series W through the theoretical framework borrowed from Lauren Berlant (“intimate public”, “female complaint”) and Gayle Letherby (“auto/biography”).","source":"DOAJ","year":2023,"language":"","subjects":["Philology. Linguistics","History (General)"],"doi":"10.22394/2412-9410-2023-9-4-268-285","url":"https://steps.ranepa.ru/jour/article/view/200","is_open_access":true,"published_at":"","score":67},{"id":"doaj_10.4000/11tb1","title":"Traces of Solidarity in Liberation Training Sites in Angola","authors":[{"name":"Justin Pearce"}],"abstract":"From the mid-1970s until the late 1980s, Angola hosted guerrillas fighting for the liberation of other southern African states, as well as Cuban and Soviet military advisors and civilian professionals. As the study of Cold War era liberation struggles has developed from nation-centred narratives towards both global and local perspectives, the international encounters that took place in the ambit of these struggles have attracted attention from several historians. In particular, the military training camps have come to be seen as an environment that nurtured specific kinds of social and political relationships, although little physical evidence of these camps remains. This article is based on photographs taken at Camalundu and Caculama, two sites in the Angolan Malanje province where the remains of camps are still visible. At Camalundu, Portuguese colonial architecture points to the original function of the site, while slogans painted in English and Spanish, variously referencing South African history and global revolutionary movements, bear witness to the presence of Cubans and South Africans, and provide evidence of how they saw their own role within the international politics of the day. At Caculama the secluded and defensive nature of the site and its installations provides evidence of the South African role in relation to Angolan strategic thinking. The photographs complement the existing memoirs and oral testimony about the politics of exile and about life in the camps, providing diverse evidence about the presence of liberation fighters and their relationships with the wider world. They also enable the preservation of a visual and tangible historical record which, in the absence of preservation measures, is in danger of decay beyond recognition.","source":"DOAJ","year":2023,"language":"","subjects":["Social Sciences"],"doi":"10.4000/11tb1","url":"https://journals.openedition.org/sources/917","is_open_access":true,"published_at":"","score":67},{"id":"arxiv_2307.03437","title":"Photography principle, data transmission, and invariants of manifolds","authors":[{"name":"L. Kauffman"},{"name":"V. O. Manturov"},{"name":"I. M. Nikonov"},{"name":"S. Kim"}],"abstract":"In the present paper we develop the techniques suggested in \\cite{ManturovNikonov} and the photography principle \\cite{ManturovWan} for constructing an invariant of 3-manifolds based on Ptolemy relation. We show that a direct implementation of the techniques leads to a trivial invariant and discuss how this approach can be improved to circumvent the difficulties encountered.","source":"arXiv","year":2023,"language":"en","subjects":["math.GT"],"url":"https://arxiv.org/abs/2307.03437","pdf_url":"https://arxiv.org/pdf/2307.03437","is_open_access":true,"published_at":"2023-07-07T07:49:43Z","score":67},{"id":"arxiv_2308.01379","title":"Computational Long Exposure Mobile Photography","authors":[{"name":"Eric Tabellion"},{"name":"Nikhil Karnad"},{"name":"Noa Glaser"},{"name":"Ben Weiss"},{"name":"David E. Jacobs"},{"name":"Yael Pritch"}],"abstract":"Long exposure photography produces stunning imagery, representing moving elements in a scene with motion-blur. It is generally employed in two modalities, producing either a foreground or a background blur effect. Foreground blur images are traditionally captured on a tripod-mounted camera and portray blurred moving foreground elements, such as silky water or light trails, over a perfectly sharp background landscape. Background blur images, also called panning photography, are captured while the camera is tracking a moving subject, to produce an image of a sharp subject over a background blurred by relative motion. Both techniques are notoriously challenging and require additional equipment and advanced skills. In this paper, we describe a computational burst photography system that operates in a hand-held smartphone camera app, and achieves these effects fully automatically, at the tap of the shutter button. Our approach first detects and segments the salient subject. We track the scene motion over multiple frames and align the images in order to preserve desired sharpness and to produce aesthetically pleasing motion streaks. We capture an under-exposed burst and select the subset of input frames that will produce blur trails of controlled length, regardless of scene or camera motion velocity. We predict inter-frame motion and synthesize motion-blur to fill the temporal gaps between the input frames. Finally, we composite the blurred image with the sharp regular exposure to protect the sharpness of faces or areas of the scene that are barely moving, and produce a final high resolution and high dynamic range (HDR) photograph. Our system democratizes a capability previously reserved to professionals, and makes this creative style accessible to most casual photographers.   More information and supplementary material can be found on our project webpage: https://motion-mode.github.io/","source":"arXiv","year":2023,"language":"en","subjects":["cs.CV","cs.GR","cs.LG"],"doi":"10.1145/3592124","url":"https://arxiv.org/abs/2308.01379","pdf_url":"https://arxiv.org/pdf/2308.01379","is_open_access":true,"published_at":"2023-08-02T18:36:54Z","score":67},{"id":"arxiv_2207.06004","title":"Lippmann Photography: A Signal Processing Perspective","authors":[{"name":"Gilles Baechler"},{"name":"Michalina Pacholska"},{"name":"Arnaud Latty"},{"name":"Adam Scholefield"},{"name":"Martin Vetterli"}],"abstract":"Lippmann (or interferential) photography is the first and only analog photography method that can capture the full color spectrum of a scene in a single take. This technique, invented more than a hundred years ago, records the colors by creating interference patterns inside the photosensitive plate. Lippmann photography provides a great opportunity to demonstrate several fundamental concepts in signal processing. Conversely, a signal processing perspective enables us to shed new light on the technique. In our previous work, we analyzed the spectra of historical Lippmann plates using our own mathematical model. In this paper, we provide the derivation of this model and validate it experimentally. We highlight new behaviors whose explanations were ignored by physicists to date. In particular, we show that the spectra generated by Lippmann plates are in fact distorted versions of the original spectra. We also show that these distortions are influenced by the thickness of the plate and the reflection coefficient of the reflective medium used in the capture of the photographs. We verify our model with extensive experiments on our own Lippmann photographs.","source":"arXiv","year":2022,"language":"en","subjects":["eess.IV"],"doi":"10.1109/TSP.2022.3191473","url":"https://arxiv.org/abs/2207.06004","pdf_url":"https://arxiv.org/pdf/2207.06004","is_open_access":true,"published_at":"2022-07-13T07:22:34Z","score":66},{"id":"arxiv_2208.10181","title":"Aesthetics Driven Autonomous Time-Lapse Photography Generation by Virtual and Real Robots","authors":[{"name":"Xiaobo Gao"},{"name":"Qi Kuang"},{"name":"Xin Jin"},{"name":"Bin Zhou"},{"name":"Boyan Dong"},{"name":"Xunyu Wang"}],"abstract":"Time-lapse photography is employed in movies and promotional films because it can reflect the passage of time in a short time and strengthen the visual attraction. However, since it takes a long time and requires the stable shooting, it is a great challenge for the photographer.   In this article, we propose a time-lapse photography system with virtual and real robots. To help users shoot time-lapse videos efficiently, we first parameterize the time-lapse photography and propose a parameter optimization method. For different parameters, different aesthetic models, including image and video aesthetic quality assessment networks, are used to generate optimal parameters. Then we propose a time-lapse photography interface to facilitate users to view and adjust parameters and use virtual robots to conduct virtual photography in a three-dimensional scene. The system can also export the parameters and provide them to real robots so that the time-lapse videos can be filmed in the real world.   In addition, we propose a time-lapse photography aesthetic assessment method that can automatically evaluate the aesthetic quality of time-lapse video.   The experimental results show that our method can efficiently obtain the time-lapse videos. We also conduct a user study. The results show that our system has the similar effect as professional photographers and is more efficient.","source":"arXiv","year":2022,"language":"en","subjects":["cs.CV"],"url":"https://arxiv.org/abs/2208.10181","pdf_url":"https://arxiv.org/pdf/2208.10181","is_open_access":true,"published_at":"2022-08-22T09:48:52Z","score":66},{"id":"arxiv_2206.12340","title":"How to hide your voice: Noise-cancelling bird photography blind","authors":[{"name":"Caner Baydur"},{"name":"Baojing Pu"},{"name":"Xiaoqing Xu"}],"abstract":"Getting close to birds is a great challenge in wildlife photography. Bird photography blinds may be the most effective and least intrusive way if properly designed. However, the acoustic design of the blinds has been overlooked so far. Herein, we present noise-cancelling blinds which allow photographing birds at close range. Firstly, we conduct a questionnaire in the eco-tourism centre located in Yunnan, China. Thus, we determine the birders' expectations of the indoor sound environment. We then identify diverse variables to examine the impact of architectural and acoustic decisions on noise propagation. Finally, we examine the acoustic performance of the blinds by considering the birds' hearing threshold. The numerical simulations are performed in the acoustics module of Comsol MultiPhysics. Our study demonstrated that photography blinds require a strong and thorough acoustic design for both human and bird well-being.","source":"arXiv","year":2022,"language":"en","subjects":["cs.HC","cs.SD","eess.AS"],"doi":"10.1007/s11356-023-27119-6","url":"https://arxiv.org/abs/2206.12340","pdf_url":"https://arxiv.org/pdf/2206.12340","is_open_access":true,"published_at":"2022-06-24T15:22:48Z","score":66},{"id":"doaj_10.1049/ipr2.12269","title":"Face hallucination based on cluster consistent dictionary learning","authors":[{"name":"Minqi Li"},{"name":"Xiangjian He"},{"name":"Kin‐Man Lam"},{"name":"Kaibing Zhang"},{"name":"Junfeng Jing"}],"abstract":"Abstract Face hallucination is a super‐resolution technique specially designed to reconstruct high‐resolution faces from low‐resolution faces. Most state‐of‐the‐art algorithms leverage position‐patch prior knowledge of human faces to better super‐resolve face images. However, most of them assume the training face dataset is sufficiently large, well cropped or aligned. This paper, proposes a novel example‐based face hallucination method, based on cluster consistent dictionary learning with the assumption that human faces have similar facial structures. In this method, the paired face image patches are firstly labelled as face areas including eyes, nose, mouth and other parts, as well as non‐face areas without requiring the training face images cropped and aligned. Then, the training patches are clustered according their labels and textures. The cluster consistent dictionary is learned to represent the low‐resolution patches and the high‐resolution patches. Finally, the high‐resolution patches of the input low‐resolution face image can be efficiently generated by using the adjusted anchored neighbourhood regression. As utilizing the labelled facial parts prior knowledge, the proposed method represents more details in the reconstruction. Experimental results demonstrate that the authors' algorithm outperforms many state‐of‐the‐art techniques for face hallucination under different datasets.","source":"DOAJ","year":2021,"language":"","subjects":["Photography","Computer software"],"doi":"10.1049/ipr2.12269","url":"https://doi.org/10.1049/ipr2.12269","is_open_access":true,"published_at":"","score":65}],"total":67959,"page":1,"page_size":20,"sources":["CrossRef","DOAJ","arXiv"],"query":"Photography"}