LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh

TL;DR

This paper introduces LIFe-GoM, a novel human rendering method that combines iterative feedback and multi-resolution Gaussian-on-Mesh representations to enable fast, high-quality, and generalizable human avatar reconstruction from sparse inputs.

Contribution

It proposes an iterative feedback framework and multi-resolution Gaussian-on-Mesh representation to improve reconstruction and rendering efficiency and quality.

Findings

Reconstructs human shape in under 1 second.

Renders at 95.1 FPS at 1024x1024 resolution.

Achieves state-of-the-art rendering quality metrics.

Abstract

Generalizable rendering of an animatable human avatar from sparse inputs relies on data priors and inductive biases extracted from training on large data to avoid scene-specific optimization and to enable fast reconstruction. This raises two main challenges: First, unlike iterative gradient-based adjustment in scene-specific optimization, generalizable methods must reconstruct the human shape representation in a single pass at inference time. Second, rendering is preferably computationally efficient yet of high resolution. To address both challenges we augment the recently proposed dual shape representation, which combines the benefits of a mesh and Gaussian points, in two ways. To improve reconstruction, we propose an iterative feedback update framework, which successively improves the canonical human shape representation during reconstruction. To achieve computationally efficient yet high-resolution rendering, we study a coupled-multi-resolution Gaussians-on-Mesh representation. We evaluate the proposed approach on the challenging THuman2.0, XHuman and AIST++ data. Our approach reconstructs an animatable representation from sparse inputs in less than 1s, renders views with 95.1FPS at $1024 \times 1024$, and achieves PSNR/LPIPS*/FID of 24.65/110.82/51.27 on THuman2.0, outperforming the state-of-the-art in rendering quality.