paper-with-me

홈 › Papers

Addressing the Shape-Radiance Ambiguity in View-Dependent Radiance Fields

2022-03-03 · Sverker Rasmuson, Erik Sintorn, Ulf Assarsson

We present a method for handling view-dependent information in radiance fields to help with convergence and quality of 3D reconstruction. Radiance fields with view-dependence suffers from the so called shape-radiance ambiguity, which can lead to incorrect geometry given a high angular resolution of view-dependent colors. We propose the addition of a difference plane in front of each camera, with the purpose of separating view-dependent and Lambertian components during training. We also propose an additional step where we train, but do not store, a low-resolution view-dependent function that helps to isolate the surface if such a separation is proven difficult. These additions have a small impact on performance and memory usage but enables reconstruction of scenes with highly specular components without any other explicit handling of view-dependence such as Spherical Harmonics.

📄 PDF Abstract BibTeX arXiv:2203.01553

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization

2023-03-31 · CVPR 2023 1 · Bingfan Zhu, Yanchao Yang, Xulong Wang, Youyi Zheng 외

We propose VDN-NeRF, a method to train neural radiance fields (NeRFs) for better geometry under non-Lambertian surface and dynamic lighting conditions that cause significant variation in the radiance of a point when view…

NeRF

Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form Color Estimation Method

2023-12-20 · NeurIPS 2023 11 · Qihang Fang, Yafei Song, Keqiang Li, Liefeng Bo

Neural radiance field (NeRF) enables the synthesis of cutting-edge realistic novel view images of a 3D scene. It includes density and color fields to model the shape and radiance of a scene, respectively. Supervised by t…

FormNeRF

NeRF++: Analyzing and Improving Neural Radiance Fields

2020-10-15 · Kai Zhang, Gernot Riegler, Noah Snavely, Vladlen Koltun

Neural Radiance Fields (NeRF) achieve impressive view synthesis results for a variety of capture settings, including 360 capture of bounded scenes and forward-facing capture of bounded and unbounded scenes. NeRF fits mul…

NeRF

SpecNeRF: Gaussian Directional Encoding for Specular Reflections

2023-12-20 · CVPR 2024 1 · Li Ma, Vasu Agrawal, Haithem Turki, Changil Kim 외

Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under com…

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

2023-03-20 · ICCV 2023 1 · Wenhang Ge, Tao Hu, Haoyu Zhao, Shu Liu 외

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-d…

3D ReconstructionMulti-View 3D ReconstructionSurface Reconstruction