# SpatialTracker: Tracking Any 2D Pixels in 3D Space

arXiv: https://arxiv.org/abs/2404.04319 · HTML: https://mlsanity.com/paper/2404.04319/

## Key facts

- Cited by 181 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 82 references that are in the map.
- First posted on arXiv 5 Apr 2024.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth](https://mlsanity.com/paper/2302.12288/) (2023)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking](https://mlsanity.com/paper/2307.15055/) (2023)
- [FlowFormer: A Transformer Architecture for Optical Flow](https://mlsanity.com/paper/2203.16194/) (2022)
- [TAP-Vid: A Benchmark for Tracking Any Point in a Video](https://mlsanity.com/paper/2211.03726/) (2022)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories](https://mlsanity.com/paper/2204.04153/) (2022)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation](https://mlsanity.com/paper/2307.14460/) (2023)
- [Layered Neural Atlases for Consistent Video Editing](https://mlsanity.com/paper/2109.11418/) (2021)
- [RAFT-3D: Scene Flow using Rigid-Motion Embeddings](https://mlsanity.com/paper/2012.00726/) (2020)
- [FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation](https://mlsanity.com/paper/2303.01237/) (2023)
- [HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds](https://mlsanity.com/paper/1906.05332/) (2019)
- [Creatures great and SMAL: Recovering the shape and motion of animals from video](https://mlsanity.com/paper/1811.05804/) (2018)
- [Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes](https://mlsanity.com/paper/2110.06192/) (2021)

## Built on by (most cited first, 30 of 181)

- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control](https://mlsanity.com/paper/2501.03847/) (2025)
- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction](https://mlsanity.com/paper/2409.18124/) (2024)
- [St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World](https://mlsanity.com/paper/2504.13152/) (2025)
- [SpatialTrackerV2: 3D Point Tracking Made Easy](https://mlsanity.com/paper/2507.12462/) (2025)
- [PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation](https://mlsanity.com/paper/2601.03782/) (2026)
- [Align3R: Aligned Monocular Depth Estimation for Dynamic Videos](https://mlsanity.com/paper/2412.03079/) (2024)
- [MotionStream: Real-Time Video Generation with Interactive Motion Controls](https://mlsanity.com/paper/2511.01266/) (2025)
- [CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation](https://mlsanity.com/paper/2502.08639/) (2025)
- [TAPVid-3D: A Benchmark for Tracking Any Point in 3D](https://mlsanity.com/paper/2407.05921/) (2024)
- [TAPIP3D: Tracking Any Point in Persistent 3D Geometry](https://mlsanity.com/paper/2504.14717/) (2025)
- [Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction](https://mlsanity.com/paper/2504.07961/) (2025)
- [DELTA: Dense Efficient Long-range 3D Tracking for any video](https://mlsanity.com/paper/2410.24211/) (2024)
- [AllTracker: Efficient Dense Point Tracking at High Resolution](https://mlsanity.com/paper/2506.07310/) (2025)
- [Efficiently Reconstructing Dynamic Scenes One D4RT at a Time](https://mlsanity.com/paper/2512.08924/) (2025)
- [Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation](https://mlsanity.com/paper/2412.06016/) (2024)
- [Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction](https://mlsanity.com/paper/2503.16318/) (2025)
- [Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling](https://mlsanity.com/paper/2410.18912/) (2024)
- [RoboScape: Physics-informed Embodied World Model](https://mlsanity.com/paper/2506.23135/) (2025)
- [I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength](https://mlsanity.com/paper/2411.06525/) (2024)
- [GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking](https://mlsanity.com/paper/2501.02690/) (2025)
- [GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors](https://mlsanity.com/paper/2504.01016/) (2025)
- [TAPNext: Tracking Any Point (TAP) as Next Token Prediction](https://mlsanity.com/paper/2504.05579/) (2025)
- [MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second](https://mlsanity.com/paper/2507.10065/) (2025)
- [Any4D: Unified Feed-Forward Metric 4D Reconstruction](https://mlsanity.com/paper/2512.10935/) (2025)

## Abstract (arXiv)

Recovering dense and long-range pixel motion in videos is a challenging problem. Part of the difficulty arises from the 3D-to-2D projection process, leading to occlusions and discontinuities in the 2D motion domain. While 2D motion can be intricate, we posit that the underlying 3D motion can often be simple and low-dimensional. In this work, we propose to estimate point trajectories in 3D space to mitigate the issues caused by image projection. Our method, named SpatialTracker, lifts 2D pixels to 3D using monocular depth estimators, represents the 3D content of each frame efficiently using a triplane representation, and performs iterative updates using a transformer to estimate 3D trajectories. Tracking in 3D allows us to leverage as-rigid-as-possible (ARAP) constraints while simultaneously learning a rigidity embedding that clusters pixels into different rigid parts. Extensive evaluation shows that our approach achieves state-of-the-art tracking performance both qualitatively and quantitatively, particularly in challenging scenarios such as out-of-plane rotation.