paper-with-me

Papers

Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation

2022-05-12 · CVPR 2022 1 · Jian Zhang, Yuanqing Zhang, Huan Fu, Xiaowei Zhou, Bowen Cai, Jinchi Huang, Rongfei Jia, Binqiang Zhao, Xing Tang

Neural Radiance Fields (NeRF) have emerged as a potent paradigm for representing scenes and synthesizing photo-realistic images. A main limitation of conventional NeRFs is that they often fail to produce high-quality renderings under novel viewpoints that are significantly different from the training viewpoints. In this paper, instead of exploiting few-shot image synthesis, we study the novel view extrapolation setting that (1) the training images can well describe an object, and (2) there is a notable discrepancy between the training and test viewpoints' distributions. We present RapNeRF (RAy Priors) as a solution. Our insight is that the inherent appearances of a 3D surface's arbitrary visible projections should be consistent. We thus propose a random ray casting policy that allows training unseen views using seen views. Furthermore, we show that a ray atlas pre-computed from the observed rays' viewing directions could further enhance the rendering quality for extrapolated views. A main limitation is that RapNeRF would remove the strong view-dependent effects because it leverages the multi-view consistency property.

📄 PDF Abstract BibTeX arXiv:2205.05922

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationNeRF

Similar Papers 제목 키워드 기반

CorresNeRF: Image Correspondence Priors for Neural Radiance Fields

2023-12-11 · NeurIPS 2023 11 · Yixing Lao, Xiaogang Xu, Zhipeng Cai, Xihui Liu 외

Neural Radiance Fields (NeRFs) have achieved impressive results in novel view synthesis and surface reconstruction tasks. However, their performance suffers under challenging scenarios with sparse input views. We present…

NeRFNovel View SynthesisSurface Reconstruction

Learning Neural Radiance Fields from Multi-View Geometry

2022-10-24 · Marco Orsingher, Paolo Zani, Paolo Medici, Massimo Bertozzi

We present a framework, called MVG-NeRF, that combines classical Multi-View Geometry algorithms and Neural Radiance Fields (NeRF) for image-based 3D reconstruction. NeRF has revolutionized the field of implicit 3D repres…

3D ReconstructionNeRFNovel View Synthesis

FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors

2024-10-21 · Chin-Yang Lin, Chung-Ho Wu, Chang-Han Yeh, Shih-Han Yen 외

Neural Radiance Fields (NeRF) face significant challenges in extreme few-shot scenarios, primarily due to overfitting and long training times. Existing methods, such as FreeNeRF and SparseNeRF, use frequency regularizati…

3D Scene ReconstructionNeRFNovel View SynthesisScheduling

FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors

2025-01-01 · CVPR 2025 1 · Chin-Yang Lin, Chung-Ho Wu, Chang-Han Yeh, Shih-Han Yen 외

Neural Radiance Fields (NeRF) face significant challenges in extreme few-shot scenarios, primarily due to overfitting and long training times. Existing methods, such as FreeNeRF and SparseNeRF, use frequency regulari…

3D Scene ReconstructionNeRFNovel View SynthesisScheduling

Digging into Depth Priors for Outdoor Neural Radiance Fields

2023-08-08 · Chen Wang, Jiadai Sun, Lina Liu, Chenming Wu 외

Neural Radiance Fields (NeRF) have demonstrated impressive performance in vision and graphics tasks, such as novel view synthesis and immersive reality. However, the shape-radiance ambiguity of radiance fields remains a …

NeRFNovel View Synthesis