Research map / 3D vision / Gaussian splatting
EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS
Sharath Girish, Kamal Gupta, Abhinav Shrivastava
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 |
|---|---|---|---|
| quantize color, rotation and opacity attributes with latent decoder (ablation) | 3D-GS · Train scene (Tanks&Temples) | Storage memory: 262MB -> 46MB | Improved |
| quantize color, rotation and opacity attributes (ablation) | 3D-GS · Train scene (Tanks&Temples) | PSNR: 21.94 -> 21.60 | Hurt |
| quantize attributes (ablation) | 3D-GS · Playroom (Deep Blending) | PSNR: 30.07 -> 30.48 | Improved |
| quantize opacity coefficients (ablation) | 3D-GS · novel view quality | floaters / artifacts (qualitative) | Improved |
| add progressive coarse-to-fine training (ablation) | EAGLES · Bicycle (Mip-NeRF360) | PSNR: 24.86 -> 25.07 | Improved |
| add progressive coarse-to-fine training (ablation) | EAGLES · Train scene (Tanks&Temples) | Number of Gaussians: 1.03M -> 0.85M | Improved |
| increase densification interval to 175 (ablation) | EAGLES · Train scene (Tanks&Temples) | Number of Gaussians: 0.85M -> 0.64M | Improved |
| add influence pruning stage (ablation) | EAGLES · Train scene (Tanks&Temples) | FPS: 202 -> 234 | Improved |
| add influence pruning stage (ablation) | EAGLES · Train scene (Tanks&Temples) | PSNR: 21.62 -> 21.65 | No clear effect |
| decrease progressive start scale below 0.3 (ablation) | EAGLES · Truck scene | PSNR | Hurt |
| use large 15x15 Gaussian filter instead of 5x5 for progressive scaling (ablation) | EAGLES · progressive scaling variants | PSNR: 23.41dB -> 23.17dB | Hurt |
| EAGLES vs 3D-GS runtime memory | EAGLES · Bicycle | training GPU memory: 17.4G -> 10G | Improved |
Later papers that compared with this method
4 later accepted papers report EAGLES as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- AdaptiveSplat: Texture Aware Controllable 3D Gaussian Allocation for Feed-Forward Reconstruction (ECCV 2026 · better on 5 of 5 shared results)
- RAP: Fast Feedforward Rendering-Free Attribute-Guided Primitive Importance Score Prediction for Efficient 3D Gaussian Splatting Processing (CVPR 2026 · better on 4 of 4 shared results)
- Locality-aware Gaussian Compression for Fast and High-quality Rendering (ICLR 2025 · better on 1 of 1 shared result)
- ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction (ICCV 2025 · better on 1 of 1 shared result)
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
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.93)
- PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting (CVPR 2025 · similarity 0.93)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.93)
- Optimized Minimal 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.92)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.92)
- FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting (CVPR 2025 · 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.
