InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Rendering
This addresses the challenge of generating high-quality novel views from limited input images for applications in computer vision and graphics, representing an incremental improvement over existing neural volume rendering methods.
The paper tackles the problem of few-shot novel view synthesis by introducing an information-theoretic regularization technique that minimizes reconstruction inconsistency due to insufficient viewpoints, achieving consistently improved performance by large margins on multiple standard benchmarks.
We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to insufficient viewpoints by imposing the entropy constraint of the density in each ray. In addition, to alleviate the potential degenerate issue when all training images are acquired from almost redundant viewpoints, we further incorporate the spatially smoothness constraint into the estimated images by restricting information gains from a pair of rays with slightly different viewpoints. The main idea of our algorithm is to make reconstructed scenes compact along individual rays and consistent across rays in the neighborhood. The proposed regularizers can be plugged into most of existing neural volume rendering techniques based on NeRF in a straightforward way. Despite its simplicity, we achieve consistently improved performance compared to existing neural view synthesis methods by large margins on multiple standard benchmarks.