UniSHARP: Universal Sharp Monocular View Synthesis
About
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-inspired encoders are jointly decoded to generate the complete Gaussian cloud. To comprehensively evaluate our method, we construct a benchmark covering diverse imaging systems across various scenes. The benchmark is further stratified by field of view (FoV) to enable fine-grained assessment of the universal monocular rendering task. Extensive experiments on the proposed benchmark demonstrate the effectiveness of UniSHARP, outperforming alternative methods by a large margin. The project page can be found at: https://insta360-research-team.github.io/Unisharp-website/
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Novel View Synthesis | RealEstate10K | PSNR24.495 | 212 | |
| Novel View Synthesis | DL3DV | PSNR19.468 | 92 | |
| Novel View Synthesis | Replica (test) | PSNR30.182 | 75 | |
| Novel View Synthesis | WildRGB-D | PSNR21.556 | 31 | |
| Novel View Synthesis | ScanNet++ Fisheye | PSNR20.66 | 3 | |
| Novel View Synthesis | OmniRooms Wide | PSNR25.243 | 3 | |
| Panoramic Novel View Synthesis | HM3D (test) | PSNR29.244 | 3 | |
| Panoramic Novel View Synthesis | OmniRooms (test) | PSNR24.004 | 3 | |
| Single-image novel view synthesis | Panoramic Images | Runtime (s)3.1 | 3 |