AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Omnidirectional 3D Scene Reconstruction from Single Image

Ren Yang, Jiahao Li, Yan Lu

NeurIPS 2025 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Omni3D, a method for reconstructing omnidirectional 3D scenes from a single image that addresses geometric distortion and cross-view inconsistency in diffusion-based novel view generation.

Problem

Single-image 3D scene reconstruction for omnidirectional (360-degree) scenes, where existing diffusion-based methods suffer from geometric distortions and inconsistencies across generated novel views.

Approach

Targets omnidirectional scene generation with a diffusion-based pipeline designed to reduce distortion and cross-view inconsistency before 3D recovery; specific mechanism not described in the available abstract.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy