Semantic Scholar Open Access 2023 78 sitasi

Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection

Wenhang Ge T. Hu Haoyu Zhao Shu Liu Yingke Chen

Lihat Sumber DOI

Abstrak

Neural implicit surface learning has shown significant progress in multi-view 3D reconstruction, where an object is represented by multilayer perceptrons that provide continuous implicit surface representation and view-dependent radiance. However, current methods often fail to accurately reconstruct reflective surfaces, leading to severe ambiguity. To overcome this issue, we propose Ref-NeuS, which aims to reduce ambiguity by attenuating the effect of reflective surfaces. Specifically, we utilize an anomaly detector to estimate an explicit reflection score with the guidance of multiview context to localize reflective surfaces. Afterward, we design a reflection-aware photometric loss that adaptively reduces ambiguity by modeling rendered color as a Gaussian distribution, with the reflection score representing the variance. We show that together with a reflection direction-dependent radiance, our model achieves high-quality surface reconstruction on reflective surfaces and outperforms the state-of-the-arts by a large margin. Besides, our model is also comparable on general surfaces.

Topik & Kata Kunci

Computer Science

Penulis (5)

Wenhang Ge

T. Hu

Haoyu Zhao

Shu Liu

Yingke Chen

Format Sitasi

APA MLA BibTeX

Ge, W., Hu, T., Zhao, H., Liu, S., Chen, Y. (2023). Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection. https://doi.org/10.1109/ICCV51070.2023.00392

Akses Cepat

Lihat di Sumber doi.org/10.1109/ICCV51070.2023.00392

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Total Sitasi: 78×
Sumber Database: Semantic Scholar
DOI: 10.1109/ICCV51070.2023.00392
Akses: Open Access ✓