Research map / 3D vision / Gaussian splatting
IE-SRGS: An Internal-External Knowledge Fusion Framework for High-Fidelity 3D Gaussian Splatting Super-Resolution
Xiang Feng, Tieshi Zhong, Shuo Chang, Weiliu Wang, Chengkai Wang, Yifei Chen, Tongyu Hu, Yuhe Wang, Zhenzhong Kuang, Xuefei Yin, Yanming Zhu
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 MV-Regulation to Mip-Splatting (ablation) | Mip-Splatting · Mip-NeRF 360 (9 scenes, 4x SR) | PSNR: 26.43 -> 26.68 | Improved |
| add external texture guidance (SwinIR) (ablation) | Mip-Splatting · Mip-NeRF 360 (9 scenes, 4x SR) | PSNR: 26.43 -> 26.69 | Improved |
| add external geometric guidance (depth) (ablation) | Mip-Splatting + external texture · Mip-NeRF 360 (9 scenes, 4x SR) | PSNR: 26.69 -> 26.72 | Improved |
| add internal texture guidance (ablation) | Mip-Splatting + external guidance · Mip-NeRF 360 (9 scenes, 4x SR) | PSNR: 26.72 -> 27.00 | Improved |
| add internal geometric guidance (ablation) | Mip-Splatting + external + internal texture · Mip-NeRF 360 (9 scenes, 4x SR) | PSNR: 27.00 -> 27.05 | Improved |
| add mask-guided texture integration (ablation) | IE-SRGS · Mip-NeRF 360 (9 scenes, 4x SR) | PSNR: 27.05 -> 27.15 | Improved |
| apply joint internal-external guidance on PSRT external backbone (ablation) | PSRT · MipNeRF-360 bicycle and stump | PSNR: 25.19 -> 25.67 | Improved |
| apply joint internal-external guidance on A-Splatting internal backbone (ablation) | A-Splatting · MipNeRF-360 bicycle and stump | PSNR: 24.14 -> 25.48 | Improved |
| set mask threshold T=1 (rely on external priors) instead of 0.9 (ablation) | IE-SRGS · MipNeRF-360 two scenes | PSNR | Hurt |
| IE-SRGS vs SRGS on training time | SRGS · MipNeRF-360 | total training time: 45mins 51s -> 54mins17s | Hurt |
| IE-SRGS vs SRGS on inference speed | SRGS · MipNeRF-360 | FPS: 92 -> 119 | Improved |
| IE-SRGS vs SRGS at 8x super-resolution | SRGS · MipNeRF-360 bicycle and stump, 8x SR | PSNR: 25.27 -> 25.64 | 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.
- Mip-splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · better on 2 of 2 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
- SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting (CVPR 2026 · similarity 0.92)
- S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- From Chaos to Clarity: 3DGS in the Dark (NeurIPS 2024 · similarity 0.89)
- FHGS: Feature-Homogenized Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- UVGS: Reimagining Unstructured 3D Gaussian Splatting using UV Mapping (CVPR 2025 · 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.
