collaborators

9 papers

cs.LG2026

DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models

Mingfeng Lin, Chengfei Cai, Lin Xu +2

Flow-matching models are now a mainstream method to image generation, but its adaptation to diverse downstream scenarios typically relies on post-training, which may cause conflict…

cs.CV2026

MixDiffusion: Mixing Diffusion-based Uni-condition Text-to-Image Generation Models for Multi-condition Image Synthesis

Pengcheng Wan, Liang Han, Lin Xu +2

Recent advances in text-to-image (T2I) generation have enabled controllable image synthesis by incorporating conditions beyond text. However, most existing diffusion-based methods…

cs.CV2026

City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion

Liang Han, Wenyuan Zhang, Junsheng Zhou +2

Multi-view 3D surface reconstruction is a longstanding challenge in computer vision. Although recent large-scale reconstruction methods based on 3D Gaussian Splatting (3DGS) achiev…

cs.CV2026

Sparse-View Surface Reconstruction using Gaussian Splatting through High-Confidence Depth Propagation with Normal Priors

Liang Han, Bangcai Wei, Junsheng Zhou +2

3D reconstruction from sparse views is a challenging task in 3D computer vision. Recent studies on 3D Gaussian Splatting (3DGS) have achieved remarkable results with sparse views i…

cs.CV2026

FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation

Mingfeng Lin, Jiakun Chen, Liang Han +1

Pixel-space diffusion has re-emerged as a promising alternative to latent-space generation because it avoids the representation bottleneck introduced by VAEs. Yet most existing met…

cs.CV2026

4C4D: 4 Camera 4D Gaussian Splatting

Junsheng Zhou, Zhifan Yang, Liang Han +4

This paper tackles the challenge of recovering 4D dynamic scenes from videos captured by as few as four portable cameras. Learning to model scene dynamics for temporally consistent…