Research map / 3D vision / Gaussian splatting
Geometry-Aware Flow Matching for Sparse-View 3D Gaussian Splatting
Abdullah Azeem, Ruisheng Wang, Qingquan Li, Abubakar Siddique
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
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene (NeurIPS 2025 · similarity 0.90)
- VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment (NeurIPS 2025 · similarity 0.90)
- Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis (NeurIPS 2024 · similarity 0.90)
- SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis (CVPR 2025 · similarity 0.90)
- ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting (NeurIPS 2026 · similarity 0.90)
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.
