Research map / 3D vision / Gaussian splatting
GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
Siwoo Lim, Sunjae Yoon, Gwanhyeong Koo, Chang D. Yoo
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 deformation iterations (K=0 to K=5) (ablation) | GADA · Mip-NeRF 360 | PSNR: 28.33 -> 28.62 | Improved |
| increase K from 5 to 7 (ablation) | GADA · Mip-NeRF 360 | PSNR: 28.62 -> 28.62 | No clear effect |
| increase K from 0 to 5 (ablation) | GADA · Mip-NeRF 360 | FPS: 61 -> 47 | Hurt |
| remove explicit visibility checks (ablation) | GADA · Mip-NeRF 360 | FPS: 18 -> 47 | Improved |
| remove explicit visibility checks (ablation) | GADA · Mip-NeRF 360 | PSNR: 28.45 -> 28.62 | Improved |
| add deformation regularization lambda2=0.01 (vs none) (ablation) | GADA · Mip-NeRF 360 | PSNR: 28.15 -> 28.62 | Improved |
| add deformation regularization lambda2=0.01 (vs none) (ablation) | GADA · Tanks & Temples | PSNR: 24.40 -> 24.92 | Improved |
| add deformation regularization lambda2=0.01 (vs none) (ablation) | GADA · Deep Blending | PSNR: 29.80 -> 30.22 | Improved |
| raise lambda2 from 0.01 to 1.0 (ablation) | GADA · Mip-NeRF 360 | PSNR: 28.62 -> 28.20 | Hurt |
| replace IBGS with GADA | IBGS · Mip-NeRF 360 | PSNR: 28.29 -> 28.62 | Improved |
| replace IBGS with GADA | IBGS · Mip-NeRF 360 | LPIPS: 0.191 -> 0.179 | Improved |
| replace IBGS with GADA | IBGS · Deep Blending | PSNR: 29.94 -> 30.22 | Improved |
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.
- IBGS — IBGS: Image-Based Gaussian Splatting (NeurIPS 2025) · better on 8 of 8 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
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.88)
- Topology-Aware 3D Gaussian Splatting: Leveraging Persistent Homology for Optimized Structural Integrity (AAAI 2025 · similarity 0.88)
- Gaussian Splatting Lucas-Kanade (ICLR 2025 · similarity 0.88)
- Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis (NeurIPS 2024 · similarity 0.88)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.88)
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.
