الباحثون

Feng Han

المنشورات 2

نسخة أولية وصول مفتوح

RenderBench: Benchmarking Render-to-Real Video Transfer with Reconstructed Digital Twins

Dicong Qiu, Zhiyuan Xu, Yaosheng Liu وآخرون · 2026

Modern video models can generate realistic videos from real appearance references and proxy renders that specify scene structure, viewpoint changes, and motion. Evaluating this render-to-real capability requires a real target video depicting the same scene evolution, paired with an editable, geometrically registered 3D …

نسخة أولية وصول مفتوح

Imagine then Verify: Affordance-Targeted Active Perception for Task-Oriented Grasping in Cluttered Scenes

Jingzhi Cui, Xuefeng Liu, Feng Han وآخرون · 2026

Task-oriented grasping (TOG) requires robots to grasp functional parts of objects (e.g., the handle of a mug for pouring), yet these affordance regions are frequently occluded in cluttered scenes. Active perception via next-best-view (NBV) planning can resolve such occlusions by moving the camera for more informative o …

المؤلفون المشاركون