Research map / 3D vision / Face and shape
NeuralPlane: Structured 3D Reconstruction in Planar Primitives with Neural Fields
Read the paperCheck your idea against 108,967 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 NeuralPlane, a neural-field method that distills geometric and semantic cues from inconsistent 2D plane observations into a unified 3D representation for multi-view planar primitive reconstruction.
Problem
Reconstructing compact 3D maps of man-made environments as planar primitives from multi-view images, where per-view 2D plane observations are inconsistent.
Approach
Distills geometric and semantic cues from inconsistent 2D plane observations into a unified 3D neural field, so that plane structure is recovered consistently across views.
Closest papers by meaning
- Self-Supervised Super-Plane for Neural 3D Reconstruction (CVPR 2023 · similarity 0.90)
- Neural Parts: Learning Expressive 3D Shape Abstractions With Invertible Neural Networks (CVPR 2021 · similarity 0.89)
- AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings (CVPR 2024 · similarity 0.88)
- Towards In-the-wild 3D Plane Reconstruction from a Single Image (CVPR 2025 · similarity 0.88)
- Neural Processing of Tri-Plane Hybrid Neural Fields (ICLR 2024 · similarity 0.87)
- AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos (NeurIPS 2024 · similarity 0.87)
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.