ZeroRF: Fast Sparse View 360° Reconstruction with Zero Pretraining

Abstract

We present ZeroRF, a novel per-scene optimization method addressing the challenge of sparse view 360° reconstruction in neural field representations. Current breakthroughs like Neural Radiance Fields (NeRF) have demonstrated high-fidelity image synthesis but struggle with sparse input views. Existing methods, such as Gener-alizable NeRFs and per-scene optimization approaches, face limitations in data dependency, computational cost, and generalization across diverse scenarios. To overcome these challenges, we propose ZeroRF, whose key idea is to integrate a tailored Deep Image Prior into a factorized NeRF representation. Unlike traditional methods, ZeroRF parametrizes feature grids with a neural network generator, enabling efficient sparse view 360° reconstruction without any pretraining or additional regularization. Extensive ex-periments showcase ZeroRF's versatility and superiority in terms of both quality and speed, achieving state-of-the-art results on benchmark datasets. ZeroRF's significance ex-tends to applications in 3D content generation and editing. Project page: https://sarahweiii.github.io/zerorf/.