TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
Local all-pair correspondence for point tracking
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
TrackCue uses dense image-space trajectories from point tracking and ego-motion compensation to improve static-dynamic classification and supervision for LiDAR scene flow estimation.
citing papers explorer
-
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
TrackCraft3R is the first method to repurpose a video diffusion transformer as a feed-forward dense 3D tracker via dual-latent representations and temporal RoPE alignment, achieving SOTA performance with lower compute.
-
Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation
TrackCue uses dense image-space trajectories from point tracking and ego-motion compensation to improve static-dynamic classification and supervision for LiDAR scene flow estimation.