# Affine-Aligned Atlas for Canonical Gaussian Construction in Video Representation

arXiv: https://arxiv.org/abs/2610.01114 · HTML: https://mlsanity.com/paper/2610.01114/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 1 Oct 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)
- [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)
- [Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting](https://mlsanity.com/paper/2310.10642/) (2023)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [NeRV: Neural Representations for Videos](https://mlsanity.com/paper/2110.13903/) (2021)
- [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)
- [A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2311.12897/) (2023)
- [Image-GS: Content-Adaptive Image Representation via 2D Gaussians](https://mlsanity.com/paper/2407.01866/) (2024)
- [Splatter a Video: Video Gaussian Representation for Versatile Processing](https://mlsanity.com/paper/2406.13870/) (2024)
- [Boosting Neural Representations for Videos with a Conditional Decoder](https://mlsanity.com/paper/2402.18152/) (2024)
- [DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes](https://mlsanity.com/paper/2403.15679/) (2024)
- [PCGS: Progressive Compression of 3D Gaussian Splatting](https://mlsanity.com/paper/2503.08511/) (2025)
- [GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting](https://mlsanity.com/paper/2501.04782/) (2025)
- [VeGaS: Video Gaussian Splatting](https://mlsanity.com/paper/2411.11024/) (2024)
- [GaussianVideo: Efficient Video Representation and Compression by Gaussian Splatting](https://mlsanity.com/paper/2503.04333/) (2025)
- [EigenGS Representation: From Eigenspace to Gaussian Image Space](https://mlsanity.com/paper/2503.07446/) (2025)
- [SR-NeRV: Improving Embedding Efficiency of Neural Video Representation via Super-Resolution](https://mlsanity.com/paper/2505.00046/) (2025)
- [GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Field](https://mlsanity.com/paper/2507.05594/) (2025)
- [Contour Information Aware 2D Gaussian Splatting for Image Representation](https://mlsanity.com/paper/2512.23255/) (2025)
- [STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation](https://mlsanity.com/paper/2604.10910/) (2026)

## Abstract (arXiv)

Gaussian splatting has recently emerged as an efficient representation for images and videos due to its explicit structure and fast rendering capability. Existing Gaussian-based video representations often decompose a video into canonical Gaussians and temporal deformation. However, when a video contains large global motion such as camera movement, the canonical representation may become misaligned with individual frames, increasing the burden on the temporal deformation model. In this paper, we propose an affine-atlas canonical Gaussian representation, which constructs canonical Gaussians in a larger affine-aligned atlas space. Frame-wise affine transforms absorb global motion before canonical Gaussian construction, reducing the gap between the canonical representation and target frames. Since the proposed method only modifies the canonical construction stage, it can be integrated into existing canonical-Gaussian-based methods with negligible additional parameter cost. Experiments show that our method improves reconstruction quality especially for sequences with large camera motion.