Geometry-aware Single-image Full-body Human Relighting

TL;DR

This paper introduces a geometry-aware framework for single-image human relighting that explicitly models shadows and improves albedo-lighting disentanglement, resulting in more realistic relighting effects.

Contribution

It combines geometry reconstruction, ray tracing, and neural rendering to enhance shadow realism and disentangle albedo and lighting more effectively.

Findings

Outperforms previous methods on synthetic images

Generates realistic high-frequency shadows including cast shadows

Achieves better albedo-lighting disentanglement

Abstract

Single-image human relighting aims to relight a target human under new lighting conditions by decomposing the input image into albedo, shape and lighting. Although plausible relighting results can be achieved, previous methods suffer from both the entanglement between albedo and lighting and the lack of hard shadows, which significantly decrease the realism. To tackle these two problems, we propose a geometry-aware single-image human relighting framework that leverages single-image geometry reconstruction for joint deployment of traditional graphics rendering and neural rendering techniques. For the de-lighting, we explore the shortcomings of UNet architecture and propose a modified HRNet, achieving better disentanglement between albedo and lighting. For the relighting, we introduce a ray tracing-based per-pixel lighting representation that explicitly models high-frequency shadows and propose a learning-based shading refinement module to restore realistic shadows (including hard cast shadows) from the ray-traced shading maps. Our framework is able to generate photo-realistic high-frequency shadows such as cast shadows under challenging lighting conditions. Extensive experiments demonstrate that our proposed method outperforms previous methods on both synthetic and real images.