5 papers
World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
Junjin Xiao, Yandan Yang, Xinyuan Chang +5
Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale dem…
Structure-Guided Diffusion Models for High-Fidelity Portrait Shadow Removal
Wanchang Yu, Qing Zhang, Rongjia Zheng +1
We present a diffusion-based portrait shadow removal approach that can robustly produce high-fidelity results. Unlike previous methods, we cast shadow removal as diffusion-based in…
DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering
Rongjia Zheng, Qing Zhang, Chengjiang Long +1
Recent methods have shown that pre-trained diffusion models can be fine-tuned to enable generative inverse rendering by learning image-conditioned noise-to-intrinsic mapping. Despi…
Domain Generalizable Portrait Style Transfer
Xinbo Wang, Wenju Xu, Qing Zhang +1
This paper presents a portrait style transfer method that generalizes well to various different domains while enabling high-quality semantic-aligned stylization on regions includin…
RoGSplat: Learning Robust Generalizable Human Gaussian Splatting from Sparse Multi-View Images
Junjin Xiao, Qing Zhang, Yonewei Nie +2
This paper presents RoGSplat, a novel approach for synthesizing high-fidelity novel views of unseen human from sparse multi-view images, while requiring no cumbersome per-subject o…