6 papers
Syn4D: A Multiview Synthetic 4D Dataset
Zeren Jiang, Yushi Lan, Yihang Luo +8
Dense 3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision. Progress in this area has been constrained by th…
CoWTracker: Tracking by Warping instead of Correlation
Zihang Lai, Eldar Insafutdinov, Edgar Sucar +1
Dense point tracking is a fundamental problem in computer vision, with applications ranging from video analysis to robotic manipulation. State-of-the-art trackers typically rely on…
V-DPM: 4D Video Reconstruction with Dynamic Point Maps
Edgar Sucar, Eldar Insafutdinov, Zihang Lai +1
Powerful 3D representations such as DUSt3R invariant point maps, which encode 3D shape and camera parameters, have significantly advanced feed forward 3D reconstruction. While poin…
Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
Zihang Lai, Andrea Vedaldi
Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution,…
Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction
Edgar Sucar, Zihang Lai, Eldar Insafutdinov +1
DUSt3R has recently shown that one can reduce many tasks in multi-view geometry, including estimating camera intrinsics and extrinsics, reconstructing the scene in 3D, and establis…
Exploring Simple Open-Vocabulary Semantic Segmentation
Zihang Lai
Open-vocabulary semantic segmentation models aim to accurately assign a semantic label to each pixel in an image from a set of arbitrary open-vocabulary texts. In order to learn su…