# TOM-GS: Editable Video Representation via Temporal Opacity Modulation of Static 3D Gaussians

arXiv: https://arxiv.org/abs/2607.22717 · HTML: https://mlsanity.com/paper/2607.22717/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 25 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [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)
- [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)
- [PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics](https://mlsanity.com/paper/2311.12198/) (2023)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting](https://mlsanity.com/paper/2311.14521/) (2023)
- [NeRV: Neural Representations for Videos](https://mlsanity.com/paper/2110.13903/) (2021)
- [Robust Dynamic Radiance Fields](https://mlsanity.com/paper/2301.02239/) (2023)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [CoDeF: Content Deformation Fields for Temporally Consistent Video Processing](https://mlsanity.com/paper/2308.07926/) (2023)
- [HNeRV: A Hybrid Neural Representation for Videos](https://mlsanity.com/paper/2304.02633/) (2023)
- [GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting](https://mlsanity.com/paper/2403.08551/) (2024)
- [E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context](https://mlsanity.com/paper/2207.08132/) (2022)
- [GaMeS: Mesh-Based Adapting and Modification of Gaussian Splatting](https://mlsanity.com/paper/2402.01459/) (2024)
- [Deformable Sprites for Unsupervised Video Decomposition](https://mlsanity.com/paper/2204.07151/) (2022)
- [DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos](https://mlsanity.com/paper/2304.06544/) (2023)
- [Splatter a Video: Video Gaussian Representation for Versatile Processing](https://mlsanity.com/paper/2406.13870/) (2024)
- [AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos](https://mlsanity.com/paper/2503.23282/) (2025)
- [GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting](https://mlsanity.com/paper/2501.04782/) (2025)
- [MiraGe: Editable 2D Images using Gaussian Splatting](https://mlsanity.com/paper/2410.01521/) (2024)
- [VeGaS: Video Gaussian Splatting](https://mlsanity.com/paper/2411.11024/) (2024)

## Abstract (arXiv)

While Implicit Neural Representations (INRs) and dynamic 3D Gaussian Splatting (3DGS) achieve impressive results in video processing, they often fall short of producing representations that are easily editable. Recent methods address this by introducing complex spatial deformations or folded distributions, which constrain optimization and reduce flexibility for downstream editing. In this paper, we introduce TOM-GS, an editable video representation that forgoes complex deformations in favor of regular 3D Gaussians equipped with a continuous temporal opacity formulation. By assigning a learnable temporal mean and scale to the opacity of each Gaussian, our model enables static 3D spatial components to fade smoothly in and out of the scene. Grounded by robust, off-the-shelf pose estimation, our approach maintains a static spatial geometry that naturally supports a wide range of manual and physics-based edits. TOM-GS outperforms prior editable video representations in visual fidelity, while its reliance on standard 3D Gaussians ensures seamless compatibility with established 3D editing tools.