UniSHARP: Universal Sharp Monocular View Synthesis
In this work, we focus on extending SHARP, the popular photorealistic view synthesis method, for universal monocular rendering across a continuum of camera systems, from conventional perspective cameras to wide-field-of-view, fisheye and omnidirectional panoramic settings. To overcome the pinhole-specific assumptions of SHARP, our key idea is to align various images in a unified omnidirectional latent space. Thus, we propose UniSHARP, which performs implicit alignment in both feature and Gaussian spaces. Specifically, Gaussian primitives are arranged along rays and radial distances in a ray-based universal representation, while 2D semantic and 3D spatial features extracted from UniK3D-ins...
| Authors | Meixi Song, Dizhe Zhang, Hao Ren et al. |
|---|---|
| Primary category | cs.CV |
| Published | 5 June 2026 |
| Last updated at source | 5 June 2026 |
Connected in the knowledge graph
- Insta360-Research/OmniRoomsDataset · cited by
Models and datasets referencing this paper
- Insta360-Research/OmniRoomsDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.