3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning

TL;DR

This paper introduces CHASE, a framework that achieves high-quality 3D human avatar reconstruction from sparse inputs by ensuring 3D consistency through novel supervision and contrastive learning techniques.

Contribution

CHASE is the first method to combine cross-pose 3D consistency supervision with geometry contrastive learning for sparse-input human avatar generation.

Findings

Outperforms state-of-the-art methods on ZJU-MoCap and H36M datasets.

Achieves dense-input-level performance with sparse inputs.

Enhances 3D consistency and detail reconstruction.

Abstract

Existing approaches for human avatar generation--both NeRF-based and 3D Gaussian Splatting (3DGS) based--struggle with maintaining 3D consistency and exhibit degraded detail reconstruction, particularly when training with sparse inputs. To address this challenge, we propose CHASE, a novel framework that achieves dense-input-level performance using only sparse inputs through two key innovations: cross-pose intrinsic 3D consistency supervision and 3D geometry contrastive learning. Building upon prior skeleton-driven approaches that combine rigid deformation with non-rigid cloth dynamics, we first establish baseline avatars with fundamental 3D consistency. To enhance 3D consistency under sparse inputs, we introduce a Dynamic Avatar Adjustment (DAA) module, which refines deformed Gaussians by leveraging similar poses from the training set. By minimizing the rendering discrepancy between adjusted Gaussians and reference poses, DAA provides additional supervision for avatar reconstruction. We further maintain global 3D consistency through a novel geometry-aware contrastive learning strategy. While designed for sparse inputs, CHASE surpasses state-of-the-art methods across both full and sparse settings on ZJU-MoCap and H36M datasets, demonstrating that our enhanced 3D consistency leads to superior rendering quality.