Neural Radiance Fields (NeRFs) have shown remarkable novel view synthesis capabilities even in large-scale, unbounded scenes, albeit requiring hundreds of views or introducing artifacts in sparser settings. Their optimization suffers from shape-radiance ambiguities wherever only a small visual overlap is available. This leads to erroneous scene geometry and artifacts. In this paper, we propose Re-Nerfing, a simple and general multi-stage approach that leverages NeRF's own view synthesis to address these limitations. With Re-Nerfing, we increase the scene's coverage and enhance the geometric consistency of novel views as follows: First, we train a NeRF with the available views. Then, we use the optimized NeRF to synthesize pseudo-views next to the original ones to simulate a stereo or trifocal setup. Finally, we train a second NeRF with both original and pseudo views while enforcing structural, epipolar constraints via the newly synthesized images. Extensive experiments on the mip-NeRF 360 dataset show the effectiveness of Re-Nerfing across denser and sparser input scenarios, bringing improvements to the state-of-the-art Zip-NeRF, even when trained with all views.

翻译：神经辐射场（NeRFs）在大规模无界场景中展现出卓越的新视角合成能力，尽管在稀疏设置下仍需数百个视角或引入伪影。在视觉重叠较小的区域，其优化过程受形状-辐射模糊性困扰，导致场景几何错误和伪影产生。本文提出Re-Nerfing——一种简单通用的多阶段方法，通过利用NeRF自身的视角合成能力解决上述局限性。该方法通过以下步骤增强场景覆盖度与新视角的几何一致性：首先，利用现有视角训练NeRF；随后，使用优化后的NeRF在原始视角旁合成伪视角，以模拟双目或三目视觉系统；最终，联合原始视角与伪视角训练第二个NeRF，并通过新合成图像施加结构化极线约束。在mip-NeRF 360数据集上的大量实验表明，Re-Nerfing在密集与稀疏输入场景中均有效，即使在使用全部视角训练时，也能提升当前最先进的Zip-NeRF性能。