3 papers
cs.CV2026
Agentic Relative Camera Pose Estimation via Learned Ranking and Verification
Zhining Gu, Shangjie Du, Weimin Qiu +3
A wide range of approaches have been developed for camera pose estimation, including correspondence-based methods, end-to-end pose regression, and recent 3D geometric foundation mo…
cs.CV2026
Learning via Self-Consistency for Diffusion-based Video Reasoning
Zhenghao Ni, Weimin Qiu, Meng Tang
Video generation models have demonstrated emerging zero-shot capabilities for visual reasoning, perception, and other vision tasks. However, diffusion-based video generation is inh…
cs.CV2024
Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects
Weimin Qiu, Jieke Wang, Meng Tang
Diffusion models achieved unprecedented fidelity and diversity for synthesizing image, video, 3D assets, etc. However, subject mixing is an unresolved issue for diffusion-based ima…