关于平面重建的论文列表,收录了多种单视角、多视角和基于深度学习等方法的重建技术。涉及到的主题包括平面提取、3D形状检测、深度学习隐函数、多视角重建、网格变形和城市重建等。
Papers
Those with piece-wise planarity are highlighted.
Plane Extraction / Detection
Title | Authors | Venue | Year | Resources |
---|
Efficient RANSAC for Point-Cloud Shape Detection | Ruwen Schnabel et al. | Computer Graphics Forum | 2007 | [PDF] [CODE] |
The 3D Hough Transform for Plane Detection in Point Clouds: A Review and a new Accumulator Design | Dorit Borrmann et al. | 3D Research | 2011 | [PDF] |
Planar Shape Detection at Structural Scales | Hao Fang et al. | CVPR | 2018 | [PDF] |
Plane Segmentation Based on the Optimal-vector-field in LiDAR Point Clouds | Sheng Xu et al. | PAMI | 2020 | [PDF] |
From Planes to Corners: Multi-Purpose Primitive Detection in Unorganized 3D Point Clouds | Christiane Sommer et al. | ICRA | 2020 | [PDF] [CODE] |
Supervised Fitting of Geometric Primitives to 3D Point Clouds | Lingxiao Li et al. | CVPR | 2019 | [PDF] [CODE] |
Highly Parallelizable Plane Extraction for Organized Point Clouds Using Spherical Convex Hulls | Hannes Möls et al. | ICRA | 2020 | [PDF] |
CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds | Eric-Tuan Lê et al. | ICCV | 2021 | [PDF] [CODE] |
Single-view Reconstruction
Title | Authors | Venue | Year | Resources |
---|
PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image | Chen Liu et al. | CVPR | 2018 | [PDF] [CODE] |
Recovering 3D Planes from a Single Image via Convolutional Neural Networks | Fengting Yang and Zihan Zhou | ECCV | 2018 | [PDF] [CODE] |
PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image | Chen Liu et al. | CVPR | 2019 | [PDF] [CODE] |
Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding | Zehao Yu et al. | CVPR | 2019 | [PDF] [CODE] |
Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks | Junyi Pan et al. | ICCV | 2019 | [PDF] [CODE] |
Mesh R-CNN | Georgia Gkioxari et al. | ICCV | 2019 | [PDF] [CODE] |
Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction | Yiming Qian and Yasutaka Furukawa | ECCV | 2020 | [PDF] |
Multi-view Reconstruction
Title | Authors | Venue | Year | Resources |
---|
Reconstructing piecewise planar scenes with multi-view regularization | Weijie Xi and Xuejin Chen | Computational Visual Media | 2019 | [PDF] |
PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo | Jiachen Liu et al. | CVPR | 2022 | [PDF] |
Generative / Implicit Field
Title | Authors | Venue | Year | Resources |
---|
Continuous Signed Distance Functions for 3D Vision | Simen Haugo et al. | 3DV | 2017 | [PDF] |
AtlasNet: A Papier-Mâché Approach to Learning 3D Surface | Thibault Groueix et al. | CVPR | 2018 | [PDF] [CODE] |
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation | Jeong Joon Park et al. | CVPR | 2019 | [PDF] [CODE] |
Occupancy Networks: Learning 3D Reconstruction in Function Space | Lars Mescheder et al. | CVPR | 2019 | [PDF] [CODE] |
Learning Implicit Fields for Generative Shape Modeling | Zhiqin Chen and Hao Zhang | CVPR | 2019 | [PDF] [CODE] |
Learning Shape Templates with Structured Implicit Functions | Kyle Genova et al. | ICCV | 2019 | [PDF] |
BSP-Net: Generating Compact Meshes via Binary Space Partitioning | Zhiqin Chen et al. | CVPR | 2020 | [PDF] [CODE] |
Points2Surf: Learning Implicit Surfaces from Point Clouds | Philipp Erler et al. | ECCV | 2020 | [PDF] [CODE] |
Overfit Neural Networks as a Compact Shape Representation | Thomas Davies et al. | arXiv | 2020 | [PDF] |
Implicit Geometric Regularization for Learning Shapes | Amos Gropp et al. | ICML | 2020 | [PDF] [CODE] |
Deep Parametric Shape Predictions using Distance Fields | Dmitriy Smirnov et al. | CVPR | 2020 | [PDF] [CODE] |
PolyGen: An Autoregressive Generative Model of 3D Meshes | Charlie Nash et al. | arXiv | 2020 | [PDF] |
CvxNet: Learnable Convex Decomposition | Boyang Deng et al. | arXiv | 2020 | [PDF] [CODE] |
Local Deep Implicit Functions for 3D Shape | Kyle Genova et al. | CVPR | 2020 | [PDF] [CODE] |
Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling | Omid Poursaeed et al. | ECCV | 2020 | [PDF] |
CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly | Fenggen Yu et al. | CVPR | 2022 | [PDF] |
Neural 3D Scene Reconstruction with the Manhattan-world Assumption | Haoyu Guo et al. | CVPR | 2022 | [PAGE] |
NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors | Jiepeng Wang et al. | ECCV | 2022 | [PAGE] |
Kinetic Reconstruction
Title | Authors | Venue | Year | Resources |
---|
KIPPI: KInetic Polygonal Partitioning of Images | JEAN-PHILIPPE BAUCHET and FLORENT LAFARGE | CVPR | 2018 | [PDF] [CODE] |
Approximating shapes in images with low-complexity polygons | Muxingzi Li et al. | CVPR | 2020 | [PDF] [CODE] |
Kinetic Shape Reconstruction | JEAN-PHILIPPE BAUCHET and FLORENT LAFARGE | SIGGRAPH | 2020 | [PDF] |
Mesh Deformation
Title | Authors | Venue | Year | Resources |
---|
Point2Mesh: A Self-Prior for Deformable Meshes | RANA HANOCKA et al. | SIGGRAPH | 2020 | [PDF] [CODE] |
ShapeFlow: Learnable Deformations Among 3D Shapes | Chiyu Jiang et al. | NeurIPS | 2020 | [PDF] [CODE] |
Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows | Kunal Gupta and Manmohan Chandraker | NeurIPS | 2020 | [PDF] [CODE] |
Learning Deformable Tetrahedral Meshes for 3D Reconstruction | Jun Gao et al. | NeurIPS | 2020 | [PDF] [CODE] |
Constructive / Parametric Geometry
Title | Authors | Venue | Year | Resources |
---|
Boolean operations on 3D selective Nef complexes: Data structure, algorithms, optimized implementation and experiments | Peter Hachenberger et al. | Computational Geometry | 2007 | [PDF] [CODE] |
Mesh arrangements for solid geometry | Qingnan Zhou et al. | SIGGRAPH | 2016 | [PDF] [CODE] |
3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks | Chuhang Zou et al. | ICCV | 2017 | [PDF] [CODE] |
CSGNet: Neural Shape Parser for Constructive Solid Geometry | Gopal Sharma et al. | CVPR | 2018 | [PDF] |
Surface Reconstruction from 3D Line Segments | Pierre-Alain Langlois et al. | 3DV | 2019 | [PDF] [CODE] |
ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds | Gopal Sharma et al. | ECCV | 2020 | [PDF] [CODE] |
PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes arXiv:1911.10949v3 | Rundi Wu et al. | CVPR | 2020 | [PDF] [CODE] |
UCSG-Net — Unsupervised Discovering of Constructive Solid Geometry Tree | Kacper Kania et al. | NIPS | 2020 | [PDF] [CODE] |
State of the Art on Computational Design of Assemblies with Rigid Parts | Ziqi Wang et al. | EUROGRAPHICS | 2021 | [PDF] |
Reconstruction of Convex Polytope Compositions from 3D Point-clouds | Markus Friedrich and Pierre-Alain Fayolle | GRAPP | 2021 | [PDF] [CODE] |
Triangulation
Title | Authors | Venue | Year | Resources |
---|
PointTriNet: Learned Triangulation of 3D Point Sets | Nicholas Sharp and Maks Ovsjanikov | ECCV | 2020 | [PDF] [CODE] |
Wireframe
Title | Authors | Venue | Year | Resources |
---|
PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds | Yujia Liu et al. | ICLR | 2021 | [PDF] |
Urban Reconstruction
Title | Authors | Venue | Year | Resources |
---|
LOD Generation for Urban Scenes | Yannick Verdie et al. | ACM TOG | 2015 | [PDF] |
Manhattan-world Urban Reconstruction from Point Clouds | Minglei Li et al. | ECCV | 2016 | [PDF] |
Connect-and-Slice: an hybrid approach for reconstructing 3D objects | Hao Fang et al. | CVPR | 2020 | [PDF] |
Relation-Constrained Automatic 3D Reconstruction of Buildings in Metropolitan Areas from Photogrammetric Point Clouds | Yuan Li and Bo Wu | Remote Sensing | 2021 | [PDF] |
Combined Rule-Based and Hypothesis-Based Method for Building Model Reconstruction from Photogrammetric Point Clouds | Linfu Xie et al. | Remote Sensing | 2021 | [PDF] |
Reconstructing Compact Building Models from Point Clouds Using Deep Implicit Fields | Zhaiyu Chen et al. | ISPRS | 2022 | [PDF] [CODE] |
Point2Roof: End-to-end 3D Building Roof Modeling from Airborne LiDAR Point Clouds | Li Li et al. | ISPRS | 2022 | [PDF] [CODE] |
License
This work is licensed under a Creative Commons Attribution 4.0 International License.