# STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation

arXiv: https://arxiv.org/abs/2604.10910 · HTML: https://mlsanity.com/paper/2604.10910/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 19 of 19)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [NeRV: Neural Representations for Videos](https://mlsanity.com/paper/2110.13903/) (2021)
- [Video Frame Interpolation via Adaptive Convolution](https://mlsanity.com/paper/1703.07514/) (2017)
- [Deep Video Inpainting](https://mlsanity.com/paper/1905.01639/) (2019)
- [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)
- [HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation](https://mlsanity.com/paper/2306.09818/) (2023)
- [Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting](https://mlsanity.com/paper/2410.20815/) (2024)
- [Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling](https://mlsanity.com/paper/2503.06617/) (2025)
- [FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos](https://mlsanity.com/paper/2212.12294/) (2022)
- [DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos](https://mlsanity.com/paper/2304.06544/) (2023)
- [DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes](https://mlsanity.com/paper/2403.15679/) (2024)
- [Instant GaussianImage: A Generalizable and Self-Adaptive Image Representation via 2D Gaussian Splatting](https://mlsanity.com/paper/2506.23479/) (2025)
- [HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting](https://mlsanity.com/paper/2412.03844/) (2024)
- [GaussianVideo: Efficient Video Representation and Compression by Gaussian Splatting](https://mlsanity.com/paper/2503.04333/) (2025)
- [GSVR: 2D Gaussian-based Video Representation for 800+ FPS with Hybrid Deformation Field](https://mlsanity.com/paper/2507.05594/) (2025)

## Built on by (most cited first, 2 of 2)

- [HyperGS: Fast and Generalizable Gaussian Video Representation](https://mlsanity.com/paper/2607.11500/) (2026)
- [Affine-Aligned Atlas for Canonical Gaussian Construction in Video Representation](https://mlsanity.com/paper/2610.01114/) (2026)

## Abstract (arXiv)

2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-agnostic or spatio-temporal feature overlapping embeddings to predict canonical Gaussian primitive deformations, which entangles static and dynamic components in videos and prevents modeling their distinct properties effectively. These result in inaccurate predictions for spatio-temporal deformations and unsatisfactory representation quality. To address these problems, this paper proposes a Spatio-Temporal hash encoding framework for Gaussian-based Video representation (STGV). By decomposing video features into learnable 2D spatial and 3D temporal hash encodings, STGV effectively facilitates the learning of motion patterns for dynamic components while maintaining background details for static elements. In addition, we construct a more stable and consistent initial canonical Gaussian representation through a key frame canonical initialization strategy, preventing from feature overlapping and a structurally incoherent geometry representation. Experimental results demonstrate that our method attains better video representation quality (+0.98 PSNR) against other Gaussian-based methods and achieves competitive performance in downstream video tasks.