CVMar 29, 2021

GNeRF: GAN-based Neural Radiance Field without Posed Camera

arXiv:2103.15606v3222 citations
Originality Highly original
AI Analysis

This addresses the limitation of requiring accurate camera poses in NeRF-based methods, enabling broader applications in computer vision and graphics.

The paper tackles the problem of Neural Radiance Field (NeRF) reconstruction in complex scenarios with unknown and randomly initialized camera poses, achieving state-of-the-art performance in novel view synthesis, especially in challenging scenes with repeated patterns or low textures.

We introduce GNeRF, a framework to marry Generative Adversarial Networks (GAN) with Neural Radiance Field (NeRF) reconstruction for the complex scenarios with unknown and even randomly initialized camera poses. Recent NeRF-based advances have gained popularity for remarkable realistic novel view synthesis. However, most of them heavily rely on accurate camera poses estimation, while few recent methods can only optimize the unknown camera poses in roughly forward-facing scenes with relatively short camera trajectories and require rough camera poses initialization. Differently, our GNeRF only utilizes randomly initialized poses for complex outside-in scenarios. We propose a novel two-phases end-to-end framework. The first phase takes the use of GANs into the new realm for optimizing coarse camera poses and radiance fields jointly, while the second phase refines them with additional photometric loss. We overcome local minima using a hybrid and iterative optimization scheme. Extensive experiments on a variety of synthetic and natural scenes demonstrate the effectiveness of GNeRF. More impressively, our approach outperforms the baselines favorably in those scenes with repeated patterns or even low textures that are regarded as extremely challenging before.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes