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.
hub
TAPIP3D: Tracking any point in persistent 3d geom- etry
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
A QA generation pipeline with True-Motion Tracking creates the 4DP-QA dataset and benchmark to improve VLM performance on motion-related 4D perception tasks.
Ground4D resolves temporal conflicts in feedforward 4D Gaussian reconstruction for off-road scenes via voxel-grounded temporal aggregation with intra-voxel softmax and surface normal regularization, outperforming prior methods on ORAD-3D and RELLIS-3D while generalizing zero-shot.
The authors release the 3DVQL benchmark for 3D multimodal visual query localization and show that a lift-and-attention fusion module outperforms prior fusion baselines on it.
ChronoFlow-Policy improves visuomotor policy learning by co-training action generation with prediction of past-current-future gripper-object keypoint trajectories.
UMA treats object motion and robot actions as co-evolving variables under a masked generative objective with hindsight relabeling and contrastive disentanglement to support multi-task pretraining and deployment across heterogeneous robot data.
A framework learns invariant symbolic reward functions from few demonstrations that generalize zero-shot to variations in robotic manipulation tasks.
A training-free Spatio-Temporal Attention Chain framework accelerates 4D mesh generation 13x, improves quality, scales to 16x longer videos, and supports downstream tracking and camera estimation.
LongDPM introduces an overlap-aware chunk-based framework that registers and fuses local dynamic reconstructions to achieve coherent long-range 4D geometry and tracking from monocular video.
Syn4D supplies multiview synthetic dynamic scenes with dense geometric, tracking and pose ground truth that lets any pixel be unprojected to any time and camera.
Velox compresses dynamic point clouds into latent tokens that support geometry via 4D surface modeling and appearance via 3D Gaussians, showing strong results on video-to-4D generation, tracking, and image-to-4D cloth simulation.
SceneScribe-1M is a new dataset of 1 million videos with semantic text, camera parameters, dense depth, and consistent 3D point tracks to support monocular depth estimation, scene reconstruction, point tracking, and text-to-video synthesis.
DePT3R performs joint dense point tracking and 3D reconstruction of dynamic scenes from multiple unposed images using a single neural network forward pass.
ArtiTwinSplat creates interactable digital twins of articulated objects from RGB-D videos via Gaussian Splatting and automatic part and joint discovery.
Human-video dynamics models enable cross-embodiment robot self-improvement via training-free Dynamics-Guided Action Correction, raising success rates from 40% to 81% on seven real-world tasks.
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.
-
4DP-QA: Scalable QA for 4D Perception in Vision Language Models
A QA generation pipeline with True-Motion Tracking creates the 4DP-QA dataset and benchmark to improve VLM performance on motion-related 4D perception tasks.
-
Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes
Ground4D resolves temporal conflicts in feedforward 4D Gaussian reconstruction for off-road scenes via voxel-grounded temporal aggregation with intra-voxel softmax and surface normal regularization, outperforming prior methods on ORAD-3D and RELLIS-3D while generalizing zero-shot.
-
Towards Visual Query Localization in the 3D World
The authors release the 3DVQL benchmark for 3D multimodal visual query localization and show that a lift-and-attention fusion module outperforms prior fusion baselines on it.
-
ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning
ChronoFlow-Policy improves visuomotor policy learning by co-training action generation with prediction of past-current-future gripper-object keypoint trajectories.
-
Unified Motion-Action Modeling for Heterogeneous Robot Learning
UMA treats object motion and robot actions as co-evolving variables under a masked generative objective with hindsight relabeling and contrastive disentanglement to support multi-task pretraining and deployment across heterogeneous robot data.
-
Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations
A framework learns invariant symbolic reward functions from few demonstrations that generalize zero-shot to variations in robotic manipulation tasks.
-
Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
A training-free Spatio-Temporal Attention Chain framework accelerates 4D mesh generation 13x, improves quality, scales to 16x longer videos, and supports downstream tracking and camera estimation.
-
LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos
LongDPM introduces an overlap-aware chunk-based framework that registers and fuses local dynamic reconstructions to achieve coherent long-range 4D geometry and tracking from monocular video.
-
Syn4D: A Multiview Synthetic 4D Dataset
Syn4D supplies multiview synthetic dynamic scenes with dense geometric, tracking and pose ground truth that lets any pixel be unprojected to any time and camera.
-
Velox: Learning Representations of 4D Geometry and Appearance
Velox compresses dynamic point clouds into latent tokens that support geometry via 4D surface modeling and appearance via 3D Gaussians, showing strong results on video-to-4D generation, tracking, and image-to-4D cloth simulation.
-
SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
SceneScribe-1M is a new dataset of 1 million videos with semantic text, camera parameters, dense depth, and consistent 3D point tracks to support monocular depth estimation, scene reconstruction, point tracking, and text-to-video synthesis.
-
DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Pass
DePT3R performs joint dense point tracking and 3D reconstruction of dynamic scenes from multiple unposed images using a single neural network forward pass.
-
ArtiTwinSplat: Interactable Digital Twin Reconstruction via Gaussian Splatting from RGB-D videos
ArtiTwinSplat creates interactable digital twins of articulated objects from RGB-D videos via Gaussian Splatting and automatic part and joint discovery.
-
Robot Self-Improvement via Human-Video Dynamics Models
Human-video dynamics models enable cross-embodiment robot self-improvement via training-free Dynamics-Guided Action Correction, raising success rates from 40% to 81% on seven real-world tasks.