# TRASE: Tracking-free 4D Segmentation and Editing

arXiv: https://arxiv.org/abs/2411.19290 · HTML: https://mlsanity.com/paper/2411.19290/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 57 references that are in the map.
- First posted on arXiv 28 Nov 2024.

## Builds on (most cited first, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation](https://mlsanity.com/paper/2205.04334/) (2022)
- [Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering](https://mlsanity.com/paper/2109.01847/) (2021)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations](https://mlsanity.com/paper/2209.03494/) (2022)
- [Segment Any 3D Gaussians](https://mlsanity.com/paper/2312.00860/) (2023)
- [ARF: Artistic Radiance Fields](https://mlsanity.com/paper/2206.06360/) (2022)
- [OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding](https://mlsanity.com/paper/2406.02058/) (2024)
- [NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects](https://mlsanity.com/paper/2303.14435/) (2023)
- [GARField: Group Anything with Radiance Fields](https://mlsanity.com/paper/2401.09419/) (2024)
- [GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation](https://mlsanity.com/paper/2403.12365/) (2024)
- [The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation](https://mlsanity.com/paper/1905.00737/) (2019)
- [Object-Centric Neural Scene Rendering](https://mlsanity.com/paper/2012.08503/) (2020)
- [OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning](https://mlsanity.com/paper/2311.11666/) (2023)

## Built on by (most cited first, 8 of 8)

- [Consistent Instance Field for Dynamic Scene Understanding](https://mlsanity.com/paper/2512.14126/) (2025)
- [Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation](https://mlsanity.com/paper/2512.22745/) (2025)
- [Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding](https://mlsanity.com/paper/2512.03601/) (2025)
- [Inst4DGS: Instance-Decomposed 4D Gaussian Splatting with Multi-Video Label Permutation Learning](https://mlsanity.com/paper/2603.18402/) (2026)
- [Do Gaussian Scenes Contain Enough Structure for Intrinsic Segmentation?](https://mlsanity.com/paper/2606.18623/) (2026)
- [Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation](https://mlsanity.com/paper/2606.22197/) (2026)
- [S4VY: Segment Anything in Feed-Forward 4D Visual Geometry](https://mlsanity.com/paper/2609.36875/) (2026)
- [Lens Flare Removal and Reconstruction](https://mlsanity.com/paper/2609.39527/) (2026)

## Abstract (arXiv)

Understanding dynamic 3D scenes is crucial for extended reality (XR) and autonomous driving. Incorporating semantic information into 3D reconstruction enables holistic scene representations, unlocking immersive and interactive applications. To this end, we introduce TRASE, a novel tracking-free 4D segmentation method for dynamic scene understanding. TRASE learns a 4D segmentation feature field in a weakly-supervised manner, leveraging a soft-mined contrastive learning objective guided by SAM masks. The resulting feature space is semantically coherent and well-separated, and final object-level segmentation is obtained via unsupervised clustering. This enables fast editing, such as object removal, composition, and style transfer, by directly manipulating the scene's Gaussians. We evaluate TRASE on five dynamic benchmarks, demonstrating state-of-the-art segmentation performance from unseen viewpoints and its effectiveness across various interactive editing tasks. Our project page is available at: https://yunjinli.github.io/project-sadg/