GOFish: Full Field-of-View Gaussian Splatting and Mesh Extraction
Overview
GOFish is a new 3D Gaussian Splatting method designed to work directly with fisheye images, enabling full field-of-view rendering and aligned mesh extraction. It outperforms prior methods in PSNR and mesh F-score on benchmark datasets, offering a LiDAR-free, simulation-ready digital twin capable of real-time rendering and full FoV ray tracing.
From arXiv Robotics — research abstracts
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · PSNR improvement: 2.28 other · Basis not reported · Differing source assertions
“scene and mesh. Across the 200{\deg} FIORD and 205{\deg} FullCircle benchmarks, GOFish improves PSNR over the best prior method by 2.28 and 1.97 dB, respectively. It also outperforms fisheye rendering baselines within their own FoVs and achieves the highest mesh F-score on FIORD and the main ScanNet++ set. Together, the Gaussian scene and mesh form a LiDAR-free, simulation-ready digital twin that renders in real tim”
Exact source · revision 1Source owner not reported
Reported quantity · PSNR improvement: 1.97 other · Basis not reported · Differing source assertions
“scene and mesh. Across the 200{\deg} FIORD and 205{\deg} FullCircle benchmarks, GOFish improves PSNR over the best prior method by 2.28 and 1.97 dB, respectively. It also outperforms fisheye rendering baselines within their own FoVs and achieves the highest mesh F-score on FIORD and the main ScanNet++ set. Together, the Gaussian scene and mesh form a LiDAR-free, simulation-ready digital twin that renders in real tim”
Exact source · revision 1Source owner not reported
Reported quantity · field of view: 200 other · Basis not reported · Differing source assertions
“scene and mesh. Across the 200{\deg} FIORD and 205{\deg} FullCircle benchmarks, GOFish improves PSNR over the best prior method by 2.28 and 1.97 dB, respectively. It also outperforms fisheye rendering baselines within their own FoVs and achieves the highest mesh F-score on FIORD and the main ScanNet++ set. Together, the Gaussian scene and mesh form a LiDAR-free, simulation-ready digital twin that renders in real tim”
Exact source · revision 1Source owner not reported
Reported quantity · field of view: 205 other · Basis not reported · Differing source assertions
“scene and mesh. Across the 200{\deg} FIORD and 205{\deg} FullCircle benchmarks, GOFish improves PSNR over the best prior method by 2.28 and 1.97 dB, respectively. It also outperforms fisheye rendering baselines within their own FoVs and achieves the highest mesh F-score on FIORD and the main ScanNet++ set. Together, the Gaussian scene and mesh form a LiDAR-free, simulation-ready digital twin that renders in real tim”
Exact source · revision 1Source owner not reported
Reported quantity · field of view: 180 other · Basis not reported · Differing source assertions
“arXiv:2610.37818v1 Announce Type: cross Abstract: Robots, autonomous vehicles, and consumer 360{\deg} cameras use fisheye lenses for wide fields of view (FoVs). Simulation-ready digital twins require photorealistic rendering across the full FoV and an aligned collision mesh. However, prior fisheye Gaussian Splatting methods only rasterize up to 180{\deg} and do not produce meshes, while Gaussian surface reconstructio”
Exact source · revision 1Source owner not reported
Reported quantity · field of view: 180 other · Basis not reported · Differing source assertions
“n methods assume pinhole training images. We present GOFish, the first 3D Gaussian Splatting surface reconstruction method to train directly on fisheye images, rasterize FoVs beyond 180{\deg}, and extract an aligned mesh from the same scene. Calibrated densification recovers the surface across the entire FoV, while Calibrated Mip Filtering and Wide-Angle Appearance Modeling keep pixel blur and lens falloff out of the”
Exact source · revision 1Source owner not reported
Evidence dependency changes (1)
- 2026-10-31T17:38:09.284Z · evidence updated · source revision 1. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalGOFish: Full Field-of-View Gaussian Splatting and Mesh Extraction
GOFish is a new 3D Gaussian Splatting method designed to work directly with fisheye images, enabling full field-of-view rendering and aligned mesh extraction. It outperforms prior methods in PSNR and mesh F-score on benchmark datasets, offering a LiDAR-free, simulation-ready digital twin capable of real-time rendering and full FoV ray tracing.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).