6 papers
HiQGS: Hierarchical Spatiotemporal Querying for Feed-Forward Gaussian Reconstruction
Qiaowei Miao, Qifeng Cheng, Yijing Guo +3
Feed-forward Gaussian reconstruction from sparse posed monocular frames requires reasoning over observations that vary jointly in viewpoint and time. Existing methods either predic…
Causal Spatiotemporal State Evolution for Monocular 4D Reconstruction
Qiaowei Miao, Yijing Guo, Lipei Zhang +4
While feed-forward models excel in static 3D geometry estimation, extending them to dynamic 4D scenes requires modeling visual geometry as a causally evolving state. Current method…
USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes
Li-Heng Chen, Haokai Pang, Chengye Su +7
Spatial representation learning for autonomous driving aims to map raw visual signals into structured 3D scene representations, where object-centric bounding boxes and rendering-or…
LiDAR Prompted Spatio-Temporal Multi-View Stereo for Autonomous Driving
Qihao Sun, Jiarun Liu, Ziqian Ni +5
Accurate metric depth is critical for autonomous driving perception and simulation, yet current approaches struggle to achieve high metric accuracy, multi-view and temporal consist…
SAM4D: Segment Anything in Camera and LiDAR Streams
Jianyun Xu, Song Wang, Ziqian Ni +4
We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) i…
Para-Lane: Multi-Lane Dataset Registering Parallel Scans for Benchmarking Novel View Synthesis
Ziqian Ni, Sicong Du, Zhenghua Hou +2
To evaluate end-to-end autonomous driving systems, a simulation environment based on Novel View Synthesis (NVS) techniques is essential, which synthesizes photo-realistic images an…