5 papers
LCG: Long-Context Consistent Image Generation with Sparse Relational Attention
Zihao Wang, Yijia Xu, Haoze Zheng +3
Recent image generation models achieve impressive quality in single-image synthesis, but often fail to maintain consistency across sequential outputs, as required in comics, storyb…
Learning Latent Proxies for Controllable Single-Image Relighting
Haoze Zheng, Zihao Wang, Xianfeng Wu +5
Single-image relighting is highly under-constrained: small illumination changes can produce large, nonlinear variations in shading, shadows, and specularities, while geometry and m…
iKap: Kinematics-aware Planning with Imperative Learning
Qihang Li, Zhuoqun Chen, Haoze Zheng +5
Trajectory planning in robotics aims to generate collision-free pose sequences that can be reliably executed. Recently, vision-to-planning systems have gained increasing attention…
SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization
Yi Du, Zhipeng Zhao, Shaoshu Su +4
Point cloud (PC) processing tasks-such as completion, upsampling, denoising, and colorization-are crucial in applications like autonomous driving and 3D reconstruction. Despite sub…
AirRoom: Objects Matter in Room Reidentification
Runmao Yao, Yi Du, Zhuoqun Chen +2
Room reidentification (ReID) is a challenging yet essential task with numerous applications in fields such as augmented reality (AR) and homecare robotics. Existing visual place re…