Skanda
@skandakoppula.bsky.social
Thrilled to release 🎯 D4RT (Dynamic 4D Reconstruction and Tracking).
🌟 SOTA results on 4D reconstruction & tracking evals
🚀 Up to 100x faster pose estimation than prior works
📍 A simple, unified interface for tracking, depth, and pose using point-wise decoding
🔗 Learn more: d4rt-paper.github.io
🌟 SOTA results on 4D reconstruction & tracking evals
🚀 Up to 100x faster pose estimation than prior works
📍 A simple, unified interface for tracking, depth, and pose using point-wise decoding
🔗 Learn more: d4rt-paper.github.io
December 8, 2025 at 11:55 PM
Thrilled to release 🎯 D4RT (Dynamic 4D Reconstruction and Tracking).
🌟 SOTA results on 4D reconstruction & tracking evals
🚀 Up to 100x faster pose estimation than prior works
📍 A simple, unified interface for tracking, depth, and pose using point-wise decoding
🔗 Learn more: d4rt-paper.github.io
🌟 SOTA results on 4D reconstruction & tracking evals
🚀 Up to 100x faster pose estimation than prior works
📍 A simple, unified interface for tracking, depth, and pose using point-wise decoding
🔗 Learn more: d4rt-paper.github.io
Reposted by Skanda
Additionally, TAPNext tracks in a purely online fashion enabling TAPNext to run with minimal latency, removing the temporal windowing required by many existing causal state of art trackers.
April 9, 2025 at 2:04 PM
Additionally, TAPNext tracks in a purely online fashion enabling TAPNext to run with minimal latency, removing the temporal windowing required by many existing causal state of art trackers.
Reposted by Skanda
We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: tap-next.github.io
April 9, 2025 at 2:04 PM
We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: tap-next.github.io