Research map / 3D vision / Gaussian splatting
GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting
Andrew Bond, Jui-Hsien Wang, Long Mai, Erkut Erdem, Aykut Erdem
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add spatial hierarchical learning to temporal-only (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 42.8404 -> 43.2110 | Improved |
| add temporal hierarchical learning to spatial-only (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 42.2068 -> 43.2110 | Improved |
| add hierarchical learning (spatial and temporal) (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 40.2016 -> 43.2110 | Improved |
| add spatial hierarchical learning (ablation) | GaussianVideo · DL3DV (1K, 540p) | training time: ~ 40 mins -> ~ 35 mins | Improved |
| add Neural ODE camera model instead of static learned camera (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 33.9304 -> 43.2110 | Improved |
| add camera model (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 21.1821 -> 43.2110 | Improved |
| use B-spline motion instead of polynomial (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 20.1871 -> 43.2110 | Improved |
| learn all SH coefficients at once instead of incremental (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 31.0736 -> 43.2110 | Improved |
| allow Gaussian scale to vary over time (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 34.1585 -> 43.2110 | Improved |
| add warping of unused Gaussians (ablation) | GaussianVideo · DL3DV (1K, 540p) | PSNR: 34.0106 -> 43.2110 | Improved |
| add hierarchical learning (spatial and temporal) (ablation) | GaussianVideo · DL3DV (1K, 540p) | LPIPS: 0.0177 -> 0.0125 | Improved |
| increase Gaussian count beyond 400K (ablation) | GaussianVideo · DL3DV and DAVIS | PSNR/SSIM/LPIPS | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- GaussianImage — GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting (ECCV 2024) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.93)
- Splatter a Video: Video Gaussian Representation for Versatile Processing (NeurIPS 2024 · similarity 0.92)
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.91)
- SfM-Free 3D Gaussian Splatting via Hierarchical Training (CVPR 2025 · similarity 0.91)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.91)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
