Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering

TL;DR

This paper introduces GP-NeRF, a geometry-guided progressive NeRF approach that enhances generalizable and efficient neural human rendering, especially under sparse views and self-occlusion, with significant speed improvements.

Contribution

It proposes a novel geometry-guided multi-view feature integration and progressive rendering pipeline for improved human body synthesis.

Findings

Outperforms state-of-the-art methods on ZJU-MoCap and THUman datasets.

Reduces rendering time by over 70%.

Effectively handles self-occlusion and sparse view inputs.

Abstract

In this work we develop a generalizable and efficient Neural Radiance Field (NeRF) pipeline for high-fidelity free-viewpoint human body synthesis under settings with sparse camera views. Though existing NeRF-based methods can synthesize rather realistic details for human body, they tend to produce poor results when the input has self-occlusion, especially for unseen humans under sparse views. Moreover, these methods often require a large number of sampling points for rendering, which leads to low efficiency and limits their real-world applicability. To address these challenges, we propose a Geometry-guided Progressive NeRF (GP-NeRF). In particular, to better tackle self-occlusion, we devise a geometry-guided multi-view feature integration approach that utilizes the estimated geometry prior to integrate the incomplete information from input views and construct a complete geometry volume for the target human body. Meanwhile, for achieving higher rendering efficiency, we introduce a progressive rendering pipeline through geometry guidance, which leverages the geometric feature volume and the predicted density values to progressively reduce the number of sampling points and speed up the rendering process. Experiments on the ZJU-MoCap and THUman datasets show that our method outperforms the state-of-the-arts significantly across multiple generalization settings, while the time cost is reduced > 70% via applying our efficient progressive rendering pipeline.