4 papers
Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimation
Shaocong Xu, Songlin Wei, Qizhe Wei +12
Transparent objects remain notoriously hard for perception systems: refraction, reflection and transmission break the assumptions behind stereo, ToF and purely discriminative monoc…
UniCalib: Targetless LiDAR-Camera Calibration via Probabilistic Flow on Unified Depth Representations
Shu Han, Xubo Zhu, Ji Wu +4
Precise LiDAR-camera calibration is crucial for integrating these two sensors into robotic systems to achieve robust perception. In applications like autonomous driving, online tar…
MAGI-1: Autoregressive Video Generation at Scale
Sand. ai, Hansi Teng, Hongyu Jia +36
We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to…
QuadricsReg: Large-Scale Point Cloud Registration using Quadric Primitives
Ji Wu, Huai Yu, Shu Han +4
In the realm of large-scale point cloud registration, designing a compact symbolic representation is crucial for efficiently processing vast amounts of data, ensuring registration…