Hasil untuk "Motion pictures"

Jungho Lee, Donghyeong Kim, Dogyoon Lee et al.

3D Gaussian Splatting (3DGS) has gained significant attention due to its high-quality novel view rendering, motivating research to address real-world challenges. A critical issue is the camera motion blur caused by movement during exposure, which hinders accurate 3D scene reconstruction. In this study, we propose CoMoGaussian, a Continuous Motion-Aware Gaussian Splatting that reconstructs precise 3D scenes from motion-blurred images while maintaining real-time rendering speed. Considering the complex motion patterns inherent in real-world camera movements, we predict continuous camera trajectories using neural ordinary differential equations (ODEs). To ensure accurate modeling, we employ rigid body transformations, preserving the shape and size of the object but rely on the discrete integration of sampled frames. To better approximate the continuous nature of motion blur, we introduce a continuous motion refinement (CMR) transformation that refines rigid transformations by incorporating additional learnable parameters. By revisiting fundamental camera theory and leveraging advanced neural ODE techniques, we achieve precise modeling of continuous camera trajectories, leading to improved reconstruction accuracy. Extensive experiments demonstrate state-of-the-art performance both quantitatively and qualitatively on benchmark datasets, which include a wide range of motion blur scenarios, from moderate to extreme blur.

Hongyi Liu, Haifeng Wang

The growing demand for structural health monitoring has driven increasing interest in high-precision motion measurement, as structural information derived from extracted motions can effectively reflect the current condition of the structure. Among various motion measurement techniques, vision-based methods stand out due to their low cost, easy installation, and large-scale measurement. However, when it comes to sub-pixel-level motion measurement, current vision-based methods either lack sufficient accuracy or require extensive manual parameter tuning (e.g., pyramid layers, target pixels, and filter parameters) to reach good precision. To address this issue, we developed a novel Gaussian kernel-based motion measurement method, which can extract the motion between different frames via tracking the location of Gaussian kernels. The motion consistency, which fits practical structural conditions, and a super-resolution constraint, are introduced to increase accuracy and robustness of our method. Numerical and experimental validations show that it can consistently reach high accuracy without customized parameter setup for different test samples.

Cheng Zheng, William Koch, Baiang Li et al.

Hierarchical structures of motion exist across research fields, including computer vision, graphics, and robotics, where complex dynamics typically arise from coordinated interactions among simpler motion components. Existing methods to model such dynamics typically rely on manually-defined or heuristic hierarchies with fixed motion primitives, limiting their generalizability across different tasks. In this work, we propose a general hierarchical motion modeling method that learns structured, interpretable motion relationships directly from data. Our method represents observed motions using graph-based hierarchies, explicitly decomposing global absolute motions into parent-inherited patterns and local motion residuals. We formulate hierarchy inference as a differentiable graph learning problem, where vertices represent elemental motions and directed edges capture learned parent-child dependencies through graph neural networks. We evaluate our hierarchical reconstruction approach on three examples: 1D translational motion, 2D rotational motion, and dynamic 3D scene deformation via Gaussian splatting. Experimental results show that our method reconstructs the intrinsic motion hierarchy in 1D and 2D cases, and produces more realistic and interpretable deformations compared to the baseline on dynamic 3D Gaussian splatting scenes. By providing an adaptable, data-driven hierarchical modeling paradigm, our method offers a formulation applicable to a broad range of motion-centric tasks. Project Page: https://light.princeton.edu/HEIR/

Aliasghar Khani, Arianna Rampini, Evan Atherton et al.

Motion generation is a cornerstone of computer graphics, animation, gaming, and robotics, enabling the creation of realistic and varied character movements. A significant limitation of existing methods is their reliance on specific skeletal structures, which restricts their versatility across different characters. To overcome this, we introduce UniMoGen, a novel UNet-based diffusion model designed for skeleton-agnostic motion generation. UniMoGen can be trained on motion data from diverse characters, such as humans and animals, without the need for a predefined maximum number of joints. By dynamically processing only the necessary joints for each character, our model achieves both skeleton agnosticism and computational efficiency. Key features of UniMoGen include controllability via style and trajectory inputs, and the ability to continue motions from past frames. We demonstrate UniMoGen's effectiveness on the 100style dataset, where it outperforms state-of-the-art methods in diverse character motion generation. Furthermore, when trained on both the 100style and LAFAN1 datasets, which use different skeletons, UniMoGen achieves high performance and improved efficiency across both skeletons. These results highlight UniMoGen's potential to advance motion generation by providing a flexible, efficient, and controllable solution for a wide range of character animations.

Rémy Degenne, David Ledvinka, Etienne Marion et al.

Brownian motion is a building block in modern probability theory. In this paper, we describe a formalization of Brownian motion using the Lean theorem prover. We build on the existing measure-theoretic foundations in Lean's mathematical library, Mathlib, and we develop several key components needed for the construction of Brownian motion, including the Carathéodory and Kolmogorov extension theorems, Gaussian measures in Banach spaces, and the Kolmogorov-Chentsov theorem for path continuity.

Joshua Harold Wiebe

This article draws out a potential encounter between Hegel and film studies. Following a line of thought instantiated by Theodor Adorno, it constructs a method of reading Hegel through cinematic formal analysis. In particular, the article argues that the speculative proposition should be thought through the structure of the dissolve. The speculative proposition is a sentence whose subject and predicate rest in uneasy relation to one another, and which is not a proposition of simple identity. Making use of a famous example from The Phenomenology of Spirit, the article elaborates the confused position of the speculative proposition and demonstrates the necessity of explanatory tools that approach the matter obliquely. In the process of making this argument, other attempts to put dialectics and montage together (notably, Eisenstein’s) are situated in relation to the instructional potential of the dissolve. Close reading of a particular dissolve taken from Moby Dick (John Huston, 1956) demonstrates the isomorphism between the mechanism of Hegelian dialectic and this particular unit of film form. The article concludes by returning to a particular speculative proposition in light of the insights gleaned from formal analysis.

Hojun Jang, Young Min Kim

We present Reusable Motion prior (ReMP), an effective motion prior that can accurately track the temporal evolution of motion in various downstream tasks. Inspired by the success of foundation models, we argue that a robust spatio-temporal motion prior can encapsulate underlying 3D dynamics applicable to various sensor modalities. We learn the rich motion prior from a sequence of complete parametric models of posed human body shape. Our prior can easily estimate poses in missing frames or noisy measurements despite significant occlusion by employing a temporal attention mechanism. More interestingly, our prior can guide the system with incomplete and challenging input measurements to quickly extract critical information to estimate the sequence of poses, significantly improving the training efficiency for mesh sequence recovery. ReMP consistently outperforms the baseline method on diverse and practical 3D motion data, including depth point clouds, LiDAR scans, and IMU sensor data. Project page is available in https://hojunjang17.github.io/ReMP.

Hongyi Liu, Haifeng Wang

Compared to contact sensors-based motion measurement, vision-based motion measurement has advantages of low cost and high efficiency and have been under active development in the past decades. This paper provides a review on existing motion measurement methods. In addition to the development of each branch of vision-based motion measurement methods, this paper also discussed the advantages and disadvantages of existing methods. Based on this discussion, it was identified that existing methods have a common limitation in optimally balancing accuracy and robustness. To address issue, we developed the Gaussian kernel-based motion measurement method. Preliminary study shows that the developed method can achieve high accuracy on simple synthesized images.

Timna Rauch

Liangchen Song, Xuan Gong, Benjamin Planche et al.

Knowing the 3D motions in a dynamic scene is essential to many vision applications. Recent progress is mainly focused on estimating the activity of some specific elements like humans. In this paper, we leverage a neural motion field for estimating the motion of all points in a multiview setting. Modeling the motion from a dynamic scene with multiview data is challenging due to the ambiguities in points of similar color and points with time-varying color. We propose to regularize the estimated motion to be predictable. If the motion from previous frames is known, then the motion in the near future should be predictable. Therefore, we introduce a predictability regularization by first conditioning the estimated motion on latent embeddings, then by adopting a predictor network to enforce predictability on the embeddings. The proposed framework PREF (Predictability REgularized Fields) achieves on par or better results than state-of-the-art neural motion field-based dynamic scene representation methods, while requiring no prior knowledge of the scene.

Emanuel A. Azcona, Byoung-Woo Kim, Nicole L. Vike et al.

Operant keypress tasks, where each action has a consequence, have been analogized to the construct of "wanting" and produce lawful relationships in humans that quantify preferences for approach and avoidance behavior. It is unknown if rating tasks without an operant framework, which can be analogized to "liking", show similar lawful relationships. We studied three independent cohorts of participants (N = 501, 506, and 4,019 participants) collected by two distinct organizations, using the same 7-point Likert scale to rate negative to positive preferences for pictures from the International Affective Picture Set. Picture ratings without an operant framework produced similar value functions, limit functions, and trade-off functions to those reported in the literature for operant keypress tasks, all with goodness of fits above 0.75. These value, limit, and trade-off functions were discrete in their mathematical formulation, recurrent across all three independent cohorts, and demonstrated scaling between individual and group curves. In all three experiments, the computation of loss aversion showed 95% confidence intervals below the value of 2, arguing against a strong overweighting of losses relative to gains, as has previously been reported for keypress tasks or games of chance with calibrated uncertainty. Graphed features from the three cohorts were similar and argue that preference assessments meet three of four criteria for lawfulness, providing a simple, short, and low-cost method for the quantitative assessment of preference without forced choice decisions, games of chance, or operant keypressing. This approach can easily be implemented on any digital device with a screen (e.g., cellphones).

Marie D. Schmidt, Tobias Glasmachers, Ioannis Iossifidis

Voluntary human motion is the product of muscle activity that results from upstream motion planning of the motor cortical areas. We show that muscle activity can be artificially generated based on motion features such as position, velocity, and acceleration. For this purpose, we specifically develop an approach based on a recurrent neural network trained in a supervised learning session; additional neural network architectures are considered and evaluated. The performance is evaluated by a new score called the zero-line score. The latter adaptively rescales the loss function of the generated signal for all channels by comparing the overall range of muscle activity and thus dynamically evaluates similarities between both signals. The model achieves a remarkable precision for previously trained motion while new motions that were not trained before still have high accuracy. Further, these models are trained on multiple subjects and thus are able to generalize across individuals. In addition, we distinguish between a general model that has been trained on several subjects, a subject-specific model, and a specific pre-trained model that uses the general model as a basis and is adapted to a specific subject afterward. The subject-specific generation of muscle activity can be further exploited to improve the rehabilitation of neuromuscular diseases with myoelectric prostheses and functional electric stimulation.

Matteo Saveriano, Felix Franzel, Dongheui Lee

In this paper, we focus on generating complex robotic trajectories by merging sequential motion primitives. A robotic trajectory is a time series of positions and orientations ending at a desired target. Hence, we first discuss the generation of converging pose trajectories via dynamical systems, providing a rigorous stability analysis. Then, we present approaches to merge motion primitives which represent both the position and the orientation part of the motion. Developed approaches preserve the shape of each learned movement and allow for continuous transitions among succeeding motion primitives. Presented methodologies are theoretically described and experimentally evaluated, showing that it is possible to generate a smooth pose trajectory out of multiple motion primitives.

Regina Karl

Around 1900, the paradigm of technological reproducibility threatened to replace the hand. As a matter of fact, though, hands speak the language of cinematic media specificity quite fluently. With its fine motor manipulations, the hand offers an intimate image of essentially human traits and showcases the logic of motion pictures at large. In addition, pointing gestures and dramatic poses establish narrative chains. A close reading of The Hands of Orlac (Orlacs Hände, Robert Wiene, 1924) will explain how hands allow for this marriage between a cinema of attraction and of narration in the Weimar period. One can discern a scientific interest for the hand in parallel with its occult implications. Orlac´s murderous hands feature both, the motif of the enchanted doppelgänger as well as newly established techniques like prosthetic labor or the use of fingerprint. Even though the topoi of the mythological and the technological hand challenged one another after World War One, occultism and scientific progress meant less of a contradiction than one might think. Instead, the hand makes explicit a discourse which was only implicit at the time: technology and its impact on works of art appear as the natural extension to the human body, rather than as a substitution.

Bahman Mirheidari, Yilin Pan, Traci Walker et al.

Cognitive decline is a sign of Alzheimer's disease (AD), and there is evidence that tracking a person's eye movement, using eye tracking devices, can be used for the automatic identification of early signs of cognitive decline. However, such devices are expensive and may not be easy-to-use for people with cognitive problems. In this paper, we present a new way of capturing similar visual features, by using the speech of people describing the Cookie Theft picture - a common cognitive testing task - to identify regions in the picture prompt that will have caught the speaker's attention and elicited their speech. After aligning the automatically recognised words with different regions of the picture prompt, we extract information inspired by eye tracking metrics such as coordinates of the area of interests (AOI)s, time spent in AOI, time to reach the AOI, and the number of AOI visits. Using the DementiaBank dataset we train a binary classifier (AD vs. healthy control) using 10-fold cross-validation and achieve an 80% F1-score using the timing information from the forced alignments of the automatic speech recogniser (ASR); this achieved around 72% using the timing information from the ASR outputs.

Chelsea Birks, Lisa Coulthard

The films of Bruno Dumont are tied to unwatchability, austerity, and a post-theological seriousness. Recently, however, Dumont has taken a surprising turn towards comedy; and yet these comedies are not without the post-theological despair that characterizes his earlier films. Taking Dumont's comedy seriously, this article frames Dumont's comedic turn not as a deviation but rather as a realignment that requires retroactive reconsideration of his oeuvre's post-theological orientation. We interrogate the philosophical implications of laughter in Dumont's work and argue that it suggests a new trajectory for the post-theological project. The work of Georges Bataille anchors our analysis of violent laughter, while Jean-Luc Nancy's post-theology structures our central argument. We read Nancy's post-theology into the construction of space and subjectivity in Dumont's earlier works, which characterize both human characters and the landscapes they inhabit with a pervasive sense of depthlessness or blankness. These features of absence often lead spectators to project emotions onto Dumont's characters, but we stress this blankness as foregrounding the essential unknowingness of the subject – something which also drives Bataille's notion of laughter. For Bataille, laughter is rooted in nonknowledge, it is a non-productive expenditure that exposes the limits of human existence. It is this horizon of death and nothingness that drives Dumont's comedies. Understood through post-theological laughter, Dumont's comedic films and TV series provide new ways of accounting for the death of God. This laughter in turn operates retroactively to productively reframe post-theological violence in his work. In short, this article contends that none of Dumont's films are meant to be taken seriously. Confronting the ethical and philosophical implications of Dumont's comedic turn, this article investigates the implications of reading his oeuvre through this divinely absurdist, post-theological comedic lens and articulates a theory of post-theology that foregrounds the radicality of laughter.

Alessandro Bratus, Maurizio Corbella

Popular music gained increasing cultural relevance in Italy during the Sessantotto (’68) — a tumultuous period essentially extending over a decade, until about 1977. Because of the ideological baggage that performance acquired in those turbulent times, representing performing musicians and the social bodies interacting with them in live contexts became a key challenge for audio/visual media such as cinema, television, radio, and the recording industry. This article attempts an intermedia approach to liveness in mediatized popular music performance by cross-examining the concurrent ways in which two of the above-mentioned media practices — namely film and record production — dealt with the increasing significance and presence of popular music performance in Italian culture at that time. The agency of media as relational frames between performers and the public was strategic in determining the affordance of new popular music genres among young Italian audiences in the 1960s and 1970s. We wish to suggest that the impact of these genres on Italian young audiences reverberated across different media, generating a set of recognizable patterns.

Nguyen The Cuong, Shashev Dmitry

Video files are files that store motion pictures and sounds like in real life. In today's world, the need for automated processing of information in video files is increasing. Automated processing of information has a wide range of application including office/home surveillance cameras, traffic control, sports applications, remote object detection, and others. In particular, detection and tracking of object movement in video file plays an important role. This article describes the methods of detecting objects in video files. Today, this problem in the field of computer vision is being studied worldwide.

David Macarthur

Despite its oft-noted ambiguities, critical reception of Ridley Scott's Blade Runner (Theatrical Cuts (1982); Director's Cut (1992); Final Cut (2007)) has tended to converge upon seeing it as a futuristic sci-fi film noir whose central concern is what it means to be human, a question that is fraught given the increasingly human-like replicants designed and manufactured by the Tyrell Corporation for human use on off-world colonies. Within the terms of this way of seeing things a great deal of discussion has been devoted to putative criteria of being human and the question whether the once-retired blade runner, Rick Deckard, is or is not a replicant. I aim to explore a radically different course of interpretation, which sees the film in fundamentally moral and religious terms. Put in the starkest light, the film is not about what makes us human but whether we can be saved from ourselves, from our terrifying inhumanity, our moral blindness.

A. Hartin

Transition probability calculations of strong field particle processes in the Furry picture, typically use fermion Volkov solutions. These solutions have a relatively complicated spinor due to the interaction of the electron spin with a strong external field, which in turn leads to unwieldy trace calculations. The simplification of these calculations would aid theoretical studies of strong field phenomena such as the predicted resonance behaviour of higher order Furry picture processes. Here, Fierz transformations of Volkov spinors are developed and applied to a 1st order and a 2nd order Furry picture process. Combined with symmetry properties, the techniques presented here are generally applicable and lead to considerable simplification of Furry picture analytic calculations.