Lei Ke

7

Papers

78

Total Citations

Papers (7)

Matching Anything by Segmenting Anything

Video Depth without Video Models

SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking

Multi-View 3D Point Tracking

ProReflow: Progressive Reflow with Decomposed Velocity

EntitySAM: Segment Everything in Video

Robust Multi-Object 4D Generation for In-the-wild Videos