Research map / 3D vision / Gaussian splatting
Seam360GS: Seamless 360deg Gaussian Splatting from Real-World Omnidirectional Images
Changha Shin, Woong Oh Cho, Seon Joo Kim
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 angular distortion (lens calibration) component (ablation) | Seam360GS · 360Roam (10 scenes) | PSNR: 25.453 -> 26.101 | Improved |
| add inter-camera gap translation (ablation) | Seam360GS · 360Roam (10 scenes) | PSNR: 25.921 -> 26.101 | Improved |
| add both gap and lens calibration (ablation) | Seam360GS · 360Roam (10 scenes) | PSNR: 25.136 -> 26.101 | Improved |
| model dual-fisheye calibration vs OmniGS | Seam360GS · Synthetic | PSNR: 32.421 -> 34.986 | Improved |
| learn gap by Gaussian translation vs OmniNeRF self-calibration | Seam360GS · Synthetic gap calibration | MAE (cm): 3.299 -> 0.1150 | Improved |
| add calibration modeling at training time | Seam360GS vs OmniGS · 360Roam Office | training time: 20m31s -> 54m47s | Hurt |
| deactivate calibration at inference with fewer Gaussians | Seam360GS vs OmniGS · 360Roam Office | test FPS: 96.52 -> 136.12 | Improved |
| vary angular distortion grid resolution from 16x32 to 128x256 (ablation) | Seam360GS · 360Roam | PSNR: below 0.2 dB difference | No clear effect |
| apply seamless calibration to raw dual-fisheye inputs | Seam360GS · raw fisheye inputs | PSNR: +0.34dB | 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.
- ODGS — ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings (NeurIPS 2024) · 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
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- Anti-Aliased 2D Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- SC-OmniGS: Self-Calibrating Omnidirectional Gaussian Splatting (ICLR 2025 · similarity 0.89)
- SplatFormer: Point Transformer for Robust 3D Gaussian Splatting (ICLR 2025 · similarity 0.89)
- 3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes (CVPR 2025 · similarity 0.88)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (CVPR 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.
