Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationNeRFSimilar Papers 제목 키워드 기반
CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
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 ReconstructionLearning Neural Radiance Fields from Multi-View Geometry
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 SynthesisFrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors
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 SynthesisSchedulingFrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors
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 SynthesisSchedulingDigging into Depth Priors for Outdoor Neural Radiance Fields
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