UniSHARP: Universal Sharp Monocular View Synthesis
Summary
UniSHARP extends SHARP for universal monocular view synthesis across diverse camera systems (perspective, fisheye, omnidirectional) by aligning images in an omnidirectional latent space with joint feature and Gaussian space alignment. The method outperforms alternatives on a new benchmark.
View Cached Full Text
Cached at: 06/08/26, 03:29 AM
Paper page - UniSHARP: Universal Sharp Monocular View Synthesis
Source: https://huggingface.co/papers/2606.07514
Abstract
UniSHARP extends SHARP for universal monocular rendering across different camera systems by aligning images in an omnidirectional latent space through joint feature and Gaussian space alignment.
In this work, we focus on extending SHARP, the popularphotorealistic view synthesismethod, foruniversal monocular renderingacross 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 unifiedomnidirectional latent space. Thus, we propose UniSHARP, which performs implicit alignment in both feature and Gaussian spaces. Specifically,Gaussian primitivesare arranged along rays and radial distances in aray-based universal representation, while 2D semantic and 3D spatial features extracted fromUniK3D-inspired encodersare jointly decoded to generate the completeGaussian 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 theuniversal monocular renderingtask. 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/
View arXiv pageView PDFProject pageGitHub9Add to collection
Get this paper in your agent:
hf papers read 2606\.07514
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2606.07514 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2606.07514 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2606.07514 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
MetaView proposes a diffusion-based monocular novel view synthesis framework that combines implicit geometry priors with metric depth guidance to achieve consistent and controllable rendering under large viewpoint changes from a single image.
Unified Panoramic Geometry Estimation via Multi-View Foundation Models
PaGeR adapts the multi-view perspective foundation model Depth Anything 3 to predict scale-invariant and metric depth, surface normals, and sky segmentation from a single equirectangular image, using a fixed cubemap representation that keeps VRAM and runtime constant. The paper also releases the ZüriPano and PanoInfinigen datasets.
HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis
HarmoHOI is a unified diffusion framework that jointly generates synchronized multi-view hand-object interaction videos and globally aligned 3D point tracks, achieving state-of-the-art performance in visual quality, motion plausibility, and multi-view geometric consistency.
UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation
UniverSat introduces a Universal Patch Encoder for Vision Transformers that enables robust, sensor-agnostic spatial feature extraction across diverse Earth Observation data types, achieving strong results on classification and segmentation benchmarks.
RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
RayDer is a unified feed-forward transformer that consolidates camera estimation, scene reconstruction, and rendering for self-supervised novel view synthesis from real-world video, achieving clean power-law scaling and strong zero-shot performance.