Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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/

Meixi Song, Dizhe Zhang, Hao Ren, Ruiyang Zhang, Bo Du, Ming-Hsuan Yang, Lu Qi• 2026

Related benchmarks

TaskDatasetResultRank
Novel View SynthesisRealEstate10K
PSNR24.495
212
Novel View SynthesisDL3DV
PSNR19.468
92
Novel View SynthesisReplica (test)
PSNR30.182
75
Novel View SynthesisWildRGB-D
PSNR21.556
31
Novel View SynthesisScanNet++ Fisheye
PSNR20.66
3
Novel View SynthesisOmniRooms Wide
PSNR25.243
3
Panoramic Novel View SynthesisHM3D (test)
PSNR29.244
3
Panoramic Novel View SynthesisOmniRooms (test)
PSNR24.004
3
Single-image novel view synthesisPanoramic Images
Runtime (s)3.1
3
Showing 9 of 9 rows

Other info

GitHub

Follow for update