4 papers
Geometric Context Transformer for Streaming 3D Reconstruction
Lin-Zhuo Chen, Jian Gao, Yihang Chen +8
Streaming 3D reconstruction aims to recover 3D information, such as camera poses and point clouds, from a video stream, which necessitates geometric accuracy, temporal consistency,…
Denoise to Track: Harnessing Video Diffusion Priors for Robust Correspondence
Tianyu Yuan, Yuanbo Yang, Lin-Zhuo Chen +2
In this work, we introduce HeFT (Head-Frequency Tracker), a zero-shot point tracking framework that leverages the visual priors of pretrained video diffusion models. To better unde…
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Jiahao Wang, Yufeng Yuan, Rujie Zheng +12
Significant progress has been made in spatial intelligence, spanning both spatial reconstruction and world exploration. However, the scalability and real-world fidelity of current…
Flow Distillation Sampling: Regularizing 3D Gaussians with Pre-trained Matching Priors
Lin-Zhuo Chen, Kangjie Liu, Youtian Lin +4
3D Gaussian Splatting (3DGS) has achieved excellent rendering quality with fast training and rendering speed. However, its optimization process lacks explicit geometric constraints…