collaborators

5 papers

cs.CV2026

GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation

Yuhao Wan, Lijuan Liu, Jingzhi Zhou +6

Previous works that leverage video models for image-to-3D scene generation often suffer from geometric distortions and blurry content. Using video generation models to implicitly m…

cs.CV2026

Direct 3D-Aware Object Insertion via Decomposed Visual Proxies

Jingbo Gong, Yikai Wang, Yushi Lan +6

Object insertion aims to seamlessly composite a reference object into a specified region of a background image. Recent diffusion-based methods achieve high visual quality but formu…

cs.CV2026

Pose-Aware Diffusion for 3D Generation

Zihan Zhou, Luxi Chen, Jingzhi Zhou +4

Generating pose-aligned 3D objects is challenging due to the spatial mismatches and transformation ambiguities inherent in decoupled canonical-then-rotate paradigms. To this end, w…

cs.CV2026

Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling

Yuan Wang, Yuhao Wan, Siming Zheng +3

Recent works have explored reference-based super-resolution (RefSR) to mitigate hallucinations in diffusion-based image restoration. A key challenge is that real-world degradations…

cs.CV2025

ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution

Yuhao Wan, Peng-Tao Jiang, Qibin Hou +4

We present ControlSR, a new method that can tame Diffusion Models for consistent real-world image super-resolution (Real-ISR). Previous Real-ISR models mostly focus on how to activ…