HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors

TL;DR

HumanSplat is a novel method that predicts 3D Gaussian Splatting properties of humans from a single image, enabling photorealistic novel-view synthesis without extensive data or optimization.

Contribution

It introduces a generalizable framework combining a multi-view diffusion model and a latent transformer with human structure priors for single-image 3D human reconstruction.

Findings

Outperforms state-of-the-art methods in photorealistic synthesis

Achieves high-fidelity texture modeling with hierarchical loss

Effective on standard benchmarks and in-the-wild images

Abstract

Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat which predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis.