FlipNeRF: Flipped Reflection Rays for Few-shot Novel View Synthesis

TL;DR

FlipNeRF introduces a novel regularization technique using flipped reflection rays to improve few-shot novel view synthesis, achieving state-of-the-art results by enhancing surface normal and depth estimation accuracy.

Contribution

The paper proposes FlipNeRF, a new regularization method utilizing flipped reflection rays to improve 3D geometry estimation in few-shot view synthesis.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effectively reduces floating artifacts across different scene structures.

Enhances feature-level consistency without additional feature extractors.

Abstract

Neural Radiance Field (NeRF) has been a mainstream in novel view synthesis with its remarkable quality of rendered images and simple architecture. Although NeRF has been developed in various directions improving continuously its performance, the necessity of a dense set of multi-view images still exists as a stumbling block to progress for practical application. In this work, we propose FlipNeRF, a novel regularization method for few-shot novel view synthesis by utilizing our proposed flipped reflection rays. The flipped reflection rays are explicitly derived from the input ray directions and estimated normal vectors, and play a role of effective additional training rays while enabling to estimate more accurate surface normals and learn the 3D geometry effectively. Since the surface normal and the scene depth are both derived from the estimated densities along a ray, the accurate surface normal leads to more exact depth estimation, which is a key factor for few-shot novel view synthesis. Furthermore, with our proposed Uncertainty-aware Emptiness Loss and Bottleneck Feature Consistency Loss, FlipNeRF is able to estimate more reliable outputs with reducing floating artifacts effectively across the different scene structures, and enhance the feature-level consistency between the pair of the rays cast toward the photo-consistent pixels without any additional feature extractor, respectively. Our FlipNeRF achieves the SOTA performance on the multiple benchmarks across all the scenarios.