Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Generator-Refiner-Examiner: A Tri-Module Data Augmentation Framework for 3D Human Avatar Learning from Monocular Videos

About

This paper addresses the challenge of reconstructing photorealistic and animatable 3D human avatars from monocular videos. While existing methods rely on combining per-subject optimization with generic human priors, they often fail to capture fine-grained details when training frames are limited. To mitigate this data scarcity, we propose TrioMan, a systematic tri-module framework for augmented 3D avatar learning. Our approach comprises three synergistic components. The Generator creates diverse unseen samples by imposing Gaussian perturbations on pose and camera. The Refiner improves the quality of generated data through one-step diffusion guided by texture and geometry cues. The Examiner selects subject-consistent samples using a dual-branch attention-based similarity evaluation. Experiments on the X-Humans and NeuMan benchmarks show that TrioMan outperforms state-of-the-art methods.

Gangjian Zhang, Jian Shu, Sicheng Yu, Wenhao Shen, Yu Feng, Hao Wang• 2026

Related benchmarks

TaskDatasetResultRank
Human ReconstructionNeuMan (test)
PSNR35.42
19
Human Avatar ReconstructionX-Humans subject 00028
PSNR33.04
6
Human Avatar ReconstructionX-Humans subject 00034
PSNR29.87
6
Human Avatar ReconstructionX-Humans subject 00087
PSNR32.82
6
Showing 4 of 4 rows

Other info

Follow for update