# TrackerSplat: Exploiting Point Tracking for Fast and Robust Dynamic 3D Gaussians Reconstruction

arXiv: https://arxiv.org/abs/2604.02586 · HTML: https://mlsanity.com/paper/2604.02586/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 2 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle](https://mlsanity.com/paper/2312.03431/) (2023)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes](https://mlsanity.com/paper/2402.03307/) (2024)
- [RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot](https://mlsanity.com/paper/2307.00595/) (2023)
- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos](https://mlsanity.com/paper/2403.01444/) (2024)
- [Editable Free-viewpoint Video Using a Layered Neural Representation](https://mlsanity.com/paper/2104.14786/) (2021)
- [Streaming Radiance Fields for 3D Video Synthesis](https://mlsanity.com/paper/2210.14831/) (2022)
- [Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos](https://mlsanity.com/paper/2406.18717/) (2024)
- [Dense Optical Tracking: Connecting the Dots](https://mlsanity.com/paper/2312.00786/) (2023)
- [Representing Long Volumetric Video with Temporal Gaussian Hierarchy](https://mlsanity.com/paper/2412.09608/) (2024)
- [DynOMo: Online Point Tracking by Dynamic Online Monocular Gaussian Reconstruction](https://mlsanity.com/paper/2409.02104/) (2024)
- [Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2505.01235/) (2025)

## Built on by (most cited first, 3 of 3)

- [TrAction: Action Recognition with Sparse Trajectories](https://mlsanity.com/paper/2606.03490/) (2026)
- [CAGS: Color-Adaptive Volumetric Video Streaming with Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2605.09279/) (2026)
- [Racing in Volume with Flow Ensembles](https://mlsanity.com/paper/2609.16310/) (2026)

## Abstract (arXiv)

Recent advancements in 3D Gaussian Splatting (3DGS) have demonstrated its potential for efficient and photorealistic 3D reconstructions, which is crucial for diverse applications such as robotics and immersive media. However, current Gaussian-based methods for dynamic scene reconstruction struggle with large inter-frame displacements, leading to artifacts and temporal inconsistencies under fast object motions. To address this, we introduce textitTrackerSplat, a novel method that integrates advanced point tracking methods to enhance the robustness and scalability of 3DGS for dynamic scene reconstruction. TrackerSplat utilizes off-the-shelf point tracking models to extract pixel trajectories and triangulate per-view pixel trajectories onto 3D Gaussians to guide the relocation, rotation, and scaling of Gaussians before training. This strategy effectively handles large displacements between frames, dramatically reducing the fading and recoloring artifacts prevalent in prior methods. By accurately positioning Gaussians prior to gradient-based optimization, TrackerSplat overcomes the quality degradation associated with large frame gaps when processing multiple adjacent frames in parallel across multiple devices, thereby boosting reconstruction throughput while preserving rendering quality. Experiments on real-world datasets confirm the robustness of TrackerSplat in challenging scenarios with significant displacements, achieving superior throughput under parallel settings and maintaining visual quality compared to baselines. The code is available at https://github.com/yindaheng98/TrackerSplat.