AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Geometry-Aware Flow Matching for Sparse-View 3D Gaussian Splatting

Abdullah Azeem, Ruisheng Wang, Qingquan Li, Abubakar Siddique

NeurIPS 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting

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 a geometry-aware flow matching approach for generalizable sparse-view 3D Gaussian Splatting, moving beyond direct feed-forward regression to the final Gaussian scene.

Problem

Generalizable feed-forward 3D Gaussian Splatting predicts Gaussian scenes from sparse images, but the prediction is usually learned as a direct map to the final Gaussian scene rather than a generative or iterative process.

Approach

Instead of strengthening evidence to the predictor (multiview aggregation, geometric cues, auxiliary supervision, surface priors), the prediction itself is learned via flow matching, a generative transport from a simple distribution to the Gaussian scene, conditioned on geometry-aware features.

Experimental setup

Builds on: flow matching 3D Gaussian Splatting

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