17 papers
SRUG: Shadow-Guided Relightable Urban Scene with Generation Model
Yonghao Zhao, Zexin Yin, Jian Yang +2
Creating relightable urban scenes from images or videos is widely useful but highly ill-posed. Urban environments are typically unbounded and extend beyond the visible regions. As…
Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
Yang Wu, Qiang Meng, Zhaojiang Liu +3
Current end-to-end autonomous driving models are fundamentally constrained by the behavioral cloning ceiling of imitation learning. While reinforcement learning offers a path to sm…
EponaV2: Driving World Model with Comprehensive Future Reasoning
Jiawei Xu, Zhizhou Zhong, Zhijian Shu +8
Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving relies heavily on expensive man…
Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation
Yixin Zhu, Zixiong Wang, Jian Yang +4
Reliable simulation evaluation of robot manipulation policies serves as a high-fidelity proxy for real-world performance. Although existing benchmarks cover a wide range of task ca…
IntrinsicWeather: Controllable Weather Editing in Intrinsic Space
Yixin Zhu, Zuo-Liang Zhu, Jian Yang +3
We present IntrinsicWeather, a diffusion-based framework for controllable weather editing in intrinsic space. Our framework includes two components based on diffusion priors: an in…
3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image
Ze-Xin Yin, Liu Liu, Xinjie Wang +4
Compositional 3D scene generation from a single view requires the simultaneous recovery of scene layout and 3D assets. Existing approaches mainly fall into two categories: feed-for…