# Trace Anything: Representing Any Video in 4D via Trajectory Fields

arXiv: https://arxiv.org/abs/2510.13802 · HTML: https://mlsanity.com/paper/2510.13802/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 69 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Builds on (most cited first, 30 of 57)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting](https://mlsanity.com/paper/2310.10642/) (2023)
- [Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video](https://mlsanity.com/paper/2012.12247/) (2020)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Dynamic View Synthesis from Dynamic Monocular Video](https://mlsanity.com/paper/2105.06468/) (2021)
- [Space-time Neural Irradiance Fields for Free-Viewpoint Video](https://mlsanity.com/paper/2011.12950/) (2020)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [MapAnything: Universal Feed-Forward Metric 3D Reconstruction](https://mlsanity.com/paper/2509.13414/) (2025)

## Built on by (most cited first, 30 of 33)

- [Any4D: Unified Feed-Forward Metric 4D Reconstruction](https://mlsanity.com/paper/2512.10935/) (2025)
- [V-DPM: 4D Video Reconstruction with Dynamic Point Maps](https://mlsanity.com/paper/2601.09499/) (2026)
- [4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere](https://mlsanity.com/paper/2602.10094/) (2026)
- [DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion](https://mlsanity.com/paper/2510.15264/) (2025)
- [Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis](https://mlsanity.com/paper/2601.14253/) (2026)
- [Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels](https://mlsanity.com/paper/2603.02573/) (2026)
- [SpatialTree: How Spatial Abilities Branch Out in MLLMs](https://mlsanity.com/paper/2512.20617/) (2025)
- [Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow](https://mlsanity.com/paper/2602.14021/) (2026)
- [SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation](https://mlsanity.com/paper/2512.03350/) (2025)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking](https://mlsanity.com/paper/2605.12587/) (2026)
- [World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible](https://mlsanity.com/paper/2606.13652/) (2026)
- [SM4RT: Learning Structured Motion Geometry for 4D Reconstruction](https://mlsanity.com/paper/2607.22534/) (2026)
- [OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields](https://mlsanity.com/paper/2607.10840/) (2026)
- [TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction](https://mlsanity.com/paper/2605.26115/) (2026)
- [μ0: A Scalable 3D Interaction-Trace World Model](https://mlsanity.com/paper/2606.13769/) (2026)
- [Holo-World: Unified Camera, Object and Weather Control for Video World Model](https://mlsanity.com/paper/2606.20083/) (2026)
- [MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model](https://mlsanity.com/paper/2606.08288/) (2026)
- [4D Primitive-Mach'e: Glueing Primitives for Persistent 4D Scene Reconstruction](https://mlsanity.com/paper/2512.16564/) (2025)
- [Fast 4D Mesh Generation by Spatio-Temporal Attention Chains](https://mlsanity.com/paper/2605.19786/) (2026)
- [Preserve, Reveal, Expand: Faithful 4D Video Editing with Region-Aware Conditioning](https://mlsanity.com/paper/2605.20961/) (2026)
- [Revisiting Articulated Parts Perception in Robot Manipulation](https://mlsanity.com/paper/2606.08103/) (2026)
- [UniQuery4R: Unified 4D Scene Reconstruction from a Single Query](https://mlsanity.com/paper/2608.17283/) (2026)
- [Point4D: Long-range 4D Motion Reconstruction](https://mlsanity.com/paper/2609.09145/) (2026)
- [VideoTok4D: A 4D-Aware Video Tokenizer for Compact World Representation](https://mlsanity.com/paper/2609.12874/) (2026)
- [LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos](https://mlsanity.com/paper/2605.17303/) (2026)
- [Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding](https://mlsanity.com/paper/2607.15054/) (2026)
- [Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking](https://mlsanity.com/paper/2608.09613/) (2026)
- [Beyond Pixels: From Video Priors to 4D Worlds](https://mlsanity.com/paper/2608.10744/) (2026)
- [Gallileo-4D: Frozen Backbone Ensemble for Dynamic 4D Reconstruction](https://mlsanity.com/paper/2608.19743/) (2026)

## Abstract (arXiv)

Effective spatio-temporal representation is fundamental to modeling, understanding, and predicting dynamics in videos. The atomic unit of a video, the pixel, traces a continuous 3D trajectory over time, serving as the primitive element of dynamics. Based on this principle, we propose representing any video as a Trajectory Field: a dense mapping that assigns a continuous 3D trajectory function of time to each pixel in every frame. With this representation, we introduce Trace Anything, a neural network that predicts the entire trajectory field in a single feed-forward pass. Specifically, for each pixel in each frame, our model predicts a set of control points that parameterizes a trajectory (i.e., a B-spline), yielding its 3D position at arbitrary query time instants. We trained the Trace Anything model on large-scale 4D data, including data from our new platform, and our experiments demonstrate that: (i) Trace Anything achieves state-of-the-art performance on our new benchmark for trajectory field estimation and performs competitively on established point-tracking benchmarks; (ii) it offers significant efficiency gains thanks to its one-pass paradigm, without requiring iterative optimization or auxiliary estimators; and (iii) it exhibits emergent abilities, including goal-conditioned manipulation, motion forecasting, and spatio-temporal fusion. Project page: https://trace-anything.github.io/.