Training 3D Gaussian splatting with a learnable dual-fisheye distortion model, then turning it off at inference, renders seamless 360-degree novel views from imperfect panoramas.
Nope-nerf: Optimising neu- ral radiance field with no pose prior
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Seam360GS: Seamless 360{\deg} Gaussian Splatting from Real-World Omnidirectional Images
Training 3D Gaussian splatting with a learnable dual-fisheye distortion model, then turning it off at inference, renders seamless 360-degree novel views from imperfect panoramas.