Research map / 3D vision / Gaussian splatting
GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
Xinjie Zhang, Xingtong Ge, Tongda Xu, Dailan He, Yan Wang, Hongwei Qin, Guo Lu, Jing Geng, Jun Zhang
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 |
|---|---|---|---|
| replace alpha blending with accumulated summation blending (ablation) | GaussianImage · Kodak (30000 Gaussians) | PSNR: 37.89 -> 38.69 | Improved |
| use 2D Gaussians instead of 3D Gaussians (ablation) | GS image representation · Kodak (30000 Gaussians) | PSNR / parameters: 37.41 -> 37.89 PSNR; 1770K -> 270K params | Improved |
| merge color coefficients and opacity into weighted color (ablation) | GaussianImage · Kodak (30000 Gaussians) | PSNR: 38.69 -> 38.57; params 270K -> 240K | No clear effect |
| use L2 loss instead of L1, SSIM, or combinations (ablation) | GaussianImage · Kodak | PSNR: 36.57 (L1+SSIM) -> 38.57 | Improved |
| Cholesky versus rotation-scaling covariance factorization (ablation) | GaussianImage · Kodak | PSNR: 38.57 vs 38.83 | No clear effect |
| add commitment loss for RVQ codebook (ablation) | GaussianImage codec · Kodak | BD-rate (%): 333.16 -> 0 | Improved |
| use RVQ for color instead of 6-bit integer quantization (ablation) | GaussianImage codec · Kodak | BD-rate (%): 7.02 -> 0 | Improved |
| use higher-bit (8-bit) quantization for covariance/color (ablation) | GaussianImage codec · Kodak | BD-rate (%): 7.02 -> 11.69 | Hurt |
| use 2D Gaussians versus I-NGP and NeuRBF for representation | image representation · Kodak / DIV2K | GPU memory and training time: Kodak training 490.61 -> 106.59 s; memory 1525 -> 419 MiB | Improved |
| add partial bits-back coding to codec (ablation) | GaussianImage codec · Kodak/DIV2K rate-distortion | rate-distortion | Improved |
Later papers that compared with this method
8 later accepted papers report GaussianImage as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.
- GaussianImage++: Boosted Image Representation and Compression with 2D Gaussian Splatting (AAAI 2026 · better on 7 of 8 shared results)
- GaINeR: Geometry-Aware Implicit Neural Representation for Image Editing (ECCV 2026 · better on 6 of 6 shared results)
- SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation (CVPR 2026 · better on 4 of 4 shared results)
- SASNet: Spatially-Adaptive Sinusoidal Networks for INRs (CVPR 2026 · better on 2 of 2 shared results)
- Complex-Valued 2D Gaussian Representation for Computer-Generated Holography (ECCV 2026 · better on 2 of 2 shared results)
- GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting (ICCV 2025 · better on 5 of 5 shared results)
- EigenGS Representation: From Eigenspace to Gaussian Image Space (CVPR 2025 · better on 3 of 4 shared results)
- MiraGe: Editable 2D Images using Gaussian Splatting (ICML 2025 · better on 3 of 3 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
- Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis (CVPR 2024 · similarity 0.90)
- Optimized Minimal 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.90)
- Large Images Are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting (AAAI 2025 · similarity 0.90)
- GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution (AAAI 2025 · similarity 0.90)
- 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering (CVPR 2024 · similarity 0.89)
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.
