Awesome Scene Understanding / Survey |
| Neural Fields in Robotics: A Survey | | | |
| Advances in Data-Driven Analysis and Synthesis of 3D Indoor Scenes | | | |
| State-of-the-art in Automatic 3D Reconstruction of Structured Indoor Environments | | | |
| [project] | | | |
| Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey | | | |
| RGBD Datasets: Past, Present and Future | | | |
| [project] | | | |
Awesome Scene Understanding / Dataset / Realistic Dataset |
| ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes | | | |
| [project] | | | |
| ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data | | | |
| [code] | 674 | about 1 year ago | |
| Zillow Indoor Dataset: Annotated Floor Plans With 360Ëš Panoramas and 3D Room Layouts | | | |
| [code] | 178 | almost 3 years ago | |
| HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures | | | |
| [project] | | | |
| OASIS: A Large-Scale Dataset for Single Image 3D in the Wild | | | |
| [project] | | | |
| 3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera | | | |
| [project] | | | |
| The Replica Dataset: A Digital Replica of Indoor Spaces | | | |
| [code] | 1,022 | over 1 year ago | |
| Matterport3D: Learning from RGB-D Data in Indoor Environments | | | |
| [project] | | | |
| Joint 2D-3D-Semantic Data for Indoor Scene Understanding | | | |
| [project] | | | |
| ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes | | | |
| [project] | | | |
| SceneNN: a Scene Meshes Dataset with aNNotations | | | |
| [project] | | | |
| SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite | | | |
| [project] | | | |
| SUN3D: A Database of Big Spaces Reconstructed using SfM and Object Labels | | | |
| [project] | | | |
| Indoor Segmentation and Support Inference from RGBD Images | | | |
| [project] | | | |
Awesome Scene Understanding / Dataset / Synthetic Dataset |
| Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation | | | |
| [project] | | | |
| R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding | | | |
| [project] | | | |
| FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes | | | |
| GeoSynth: A Photorealistic Synthetic Indoor Dataset for Scene Understanding | | | |
| [code] | 40 | almost 2 years ago | |
| MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis | | | |
| [project] | | | |
| 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics | | | |
| [project] | | | |
| Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding | | | |
| [project] | | | |
| OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets | | | |
| [project] | | | |
| Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling | | | |
| [project] | | | |
| InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset | | | |
| [project] | | | |
| SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-training on Indoor Segmentation? | | | |
| [project] | | | |
| Semantic Scene Completion from a Single Depth Image | | | |
| SceneNet: Understanding Real World Indoor Scenes With Synthetic Data | | | |
| [project] | | | |
| The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes | | | |
| [project] | | | |
Awesome Scene Understanding / Holistic Scene Understanding / Perspective Image |
| Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture | | | |
| [project] | | | |
| Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes | | | |
| [code] | 106 | about 1 year ago | |
| Holistic 3D Scene Understanding from a Single Image with Implicit Representation | | | |
| [project] | | | |
| Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image | | | |
| [code] | 424 | over 1 year ago | |
| PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points | | | |
| Hoilistc++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense | | | |
| [project] | | | |
| Complete 3D Scene Parsing from an RGBD Image | | | |
| Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation | | | |
| [project] | | | |
| Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image | | | |
| [project] | | | |
| Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene | | | |
| [project] | | | |
| Im2CAD | | | |
| [project] | | | |
| DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding | | | |
| [project] | | | |
| Emptying, Refurnishing, and Relighting Indoor Spaces | | | |
| [project] | | | |
| Scene Parsing by Integrating Function, Geometry and Appearance Models | | | |
| Understanding Indoor Scenes using 3D Geometric Phrases | | | |
| Recovering Free Space of Indoor Scenes from a Single Image | | | |
| Efficient Exact Inference for 3D Indoor Scene Understanding | | | |
| Efficient Structured Prediction for 3D Indoor Scene Understanding | | | |
| Estimating Spatial Layout of Rooms using Volumetric Reasoning about Objects and Surfaces | | | |
| Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry | | | |
Awesome Scene Understanding / Holistic Scene Understanding / Panoramic Image |
| PanoContext-Former: Panoramic Total Scene Understanding with a Transformer | | | |
| PanelNet: Understanding 360 Indoor Environment via Panel Representation | | | |
| DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization | | | |
| [code] | 90 | about 3 years ago | |
| HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features | | | |
| [Code] | 108 | over 2 years ago | |
| Automatic 3D Indoor Scene Modeling from Single Panorama | | | |
| Pano2CAD: Room Layout From A Single Panorama Image | | | |
| PanoContext: A Whole-room 3D Context Model for Panoramic Scene Understanding | | | |
| [project] | | | |
Awesome Scene Understanding / Room Layout Estimation / Perspective Image |
| CAD-Estate | 106 | about 2 years ago | |
| Matterport3D-Layout | | | |
| ScanNet-Layout | 33 | about 5 years ago | |
| Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes | | | |
| [code] | 26 | over 1 year ago | |
| ST-RoomNet: Learning Room Layout Estimation From Single Image Through Unsupervised Spatial Transformations | | | |
| Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image | | | |
| [code] | 103 | about 3 years ago | |
| RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View | | | |
| GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes | | | |
| [Matterport3D Layout Dataset] | | | |
| Structural Deep Metric Learning for Room Layout Estimation | | | |
| General 3D Room Layout from a Single View by Render-and-Compare | | | |
| [project] | | | |
| Smart Hypothesis Generation for Efficient and Robust Room Layout Estimation | | | |
| Flat2Layout: Flat Representation for Estimating Layout of General Room Types | | | |
| Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts | | | |
| RoomNet: End-to-End Room Layout Estimation | | | |
| Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation | | | |
| [project] | | | |
| A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method | | | |
| DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes | | | |
| Learning Informative Edge Maps for Indoor Scene Layout Prediction | | | |
| Rent3D: Floor-Plan Priors for Monocular Layout Estimation | | | |
| [project] | | | |
| Box In the Box: Joint 3D Layout and Object Reasoning from Single Images | | | |
| Estimating the 3D Layout of Indoor Scenes and its Clutter from Depth Sensors | | | |
| [project] | | | |
| Recovering the Spatial Layout of Cluttered Rooms | | | |
Awesome Scene Understanding / Room Layout Estimation / Panoramic Image |
| ZInD | 178 | almost 3 years ago | |
| MatterportLayout | 63 | almost 5 years ago | |
| LayoutMP3D | 27 | over 5 years ago | |
| No More Ambiguity in 360â—¦ Room Layout via Bi-Layout Estimation | | | |
| Seg2Reg: Differentiable 2D Segmentation to 1D Regression Rendering for 360 Room Layout Reconstruction | | | |
| iBARLE: imBalance-Aware Room Layout Estimation | | | |
| GPR-Net: Multi-view Layout Estimation via a Geometry-aware Panorama Registration Network | | | 📷 |
| Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputs | | | |
| U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation | | | |
| Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness | | | |
| Code | 48 | almost 2 years ago | [ ] |
| 360-MLC: Multi-view Layout Consistency for Self-training and Hyper-parameter Tuning | | | 📷 |
| [Project] | | | |
| 3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform | | | |
| [Code] | 50 | over 2 years ago | |
| 3D Room Layout Recovery Generalizing across Manhattan and Non-Manhattan Worlds | | | |
| PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation | | | 📷 |
| [code] | 3 | over 2 years ago | |
| Self-supervised 360Ëš Room Layout Estimation | | | |
| [code] | 13 | over 3 years ago | |
| LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network | | | |
| Deep3DLayout: 3D Reconstruction of an Indoor Layout from a Spherical Panoramic Image | | | |
| [project] | | | |
| Transferable End-to-end Room Layout Estimation via Implicit Encoding | | | |
| [project] | | | |
| OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas | | | |
| [code] | 2 | over 4 years ago | |
| LED2-Net: Monocular 360Ëš Layout Estimation via Differentiable Depth Rendering | | | |
| [project] | | | |
| SSLayout360: Semi-Supervised Indoor Layout Estimation from 360 Panorama | | | |
| Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas | | | |
| [project] | | | |
| Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methods | | | |
| [code] | 222 | almost 4 years ago | |
| Training and Post Processing 3D Room Layout Beyond the Manhattan World Assumption | | | |
| Joint 3D Layout and Depth Prediction from a Single Indoor Panorama Image | | | |
| AtlantaNet: Inferring the 3D Indoor Layout from a Single 360 Image Beyond the Manhattan World Assumption | | | |
| [project] | | | |
| Corners for Layout: End-to-End Layout Recovery from 360 Images | | | |
| [project] | | | |
| DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama | | | |
| [project] | | | |
| HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation | | | |
| [code] | 325 | over 1 year ago | |
| Layouts from Panoramic Images with Geometry and Deep Learning | | | |
| [code] | 46 | over 5 years ago | |
| LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image | | | |
| [code] | 419 | almost 5 years ago | |
| Efficient 3D Room Shape Recovery From a Single Panorama | | | |
| [code] | 111 | over 8 years ago | |
Awesome Scene Understanding / Floorplan |
| FRI-Net: Floorplan Reconstruction via Room-wise Implicit Representation | | | 🎲 |
| [code] | 13 | over 1 year ago | |
| PolyRoom: Room-aware Transformer for Floorplan Reconstruction | | | 🎲 |
| [code] | 27 | over 1 year ago | |
| PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models | | | 🎲 |
| [project] | | | |
| Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries | | | 🎲 |
| [project] | | | |
| Floorplan Restoration by Structure Hallucinating Transformer Cascades | | | 📷 |
| MVLayoutNet: 3D Layout Reconstruction with Multi-View Panoramas | | | 📷 |
| Extreme Structure From Motion for Indoor Panoramas Without Visual Overlaps | | | 📷 |
| [code] | 35 | almost 4 years ago | |
| MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans | | | 🎲 |
| Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes | | | 🎲 |
| Floor-SP: Inverse CAD for Floorplans by Sequential Room-wise Shortest Path | | | 🎲 |
| [project] | | | |
| Floorplan-Jigsaw: Jointly Estimating Scene Layout and Aligning Partial Scans | | | 📷 |
| [project] | | | |
| DeepPerimeter: Indoor Boundary Estimation from Posed Monocular Sequences | | | 🎲 |
| FloorNet: A unified framework for floorplan reconstruction from 3D scans | | | 📷 |
| [project] | | | |
Awesome Scene Understanding / Floorplan / Floorplan Vectorization |
| VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation | | | |
| [code] | 45 | almost 2 years ago | |
| Parsing Line Segments of Floor Plan Images Using Graph Neural Networks | | | |
| Residential floor plan recognition and reconstruction | | | |
| Versailles-FP dataset: Wall Detection in Ancient Floor Plans | | | |
| Deep Floor Plan Recognition using a Multi-task Network with Room-boundary-Guided Attention | | | |
| [project] | 288 | almost 2 years ago | |
| CubiCasa5K: A Dataset and an Improved Multi-Task Model for Floorplan Image Analysis | | | |
| [code] | 310 | almost 3 years ago | |
| Raster-to-Vector: Revisiting Floorplan Transformation | | | |
| [project] | | | |
Awesome Scene Understanding / Floorplan / Visual Localization |
| SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments | | | |
| [project] | | | |
| LaLaLoc++: Global Floor Plan Comprehension for Layout Localisation in Unvisited Environments | | | |
| [code] | 23 | about 3 years ago | |
| LASER: LAtent SpacE Rendering for 2D Visual Localization | | | |
| LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments | | | |
Awesome Scene Understanding / Primitive / Junction |
| Manhattan Junction Catalogue for Spatial Reasoning of Indoor Scenes | | | |
Awesome Scene Understanding / Primitive / Line Segment and Wireframe |
| Volumetric Wireframe Parsing from Neural Attraction Fields | | | 📷 |
| code | 55 | over 1 year ago | [ ] |
| NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images | | | 📷 |
| [project] | | | |
| DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients | | | |
| [Code] | 497 | 11 months ago | |
| Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning | | | |
| Learning to Construct 3D Building Wireframes from 3D Line Clouds | | | 🎲 |
| [Code] | 41 | almost 3 years ago | |
| HoW-3D: Holistic 3D Wireframe Perception from a Single Image | | | |
| [Code] | 37 | about 3 years ago | |
| Semantic Room Wireframe Detection from a Single View | | | |
| [code] | 72 | over 2 years ago | |
| Towards Real-time and Light-weight Line Segment Detection | | | |
| [code] | 543 | over 2 years ago | |
| Hole-robust Wireframe Detection | | | |
| Fully Convolutional Line Parsing | | | |
| [code] | 156 | about 1 year ago | |
| ELSD: Efficient Line Segment Detector and Descriptor | | | |
| SOLD2: Self-supervised Occlusion-aware Line Description and Detection | | | |
| [code] | 549 | almost 2 years ago | |
| Line Segment Detection Using Transformers without Edges | | | |
| [code] | 211 | over 1 year ago | |
| PlueckerNet: Learn to Register 3D Line Reconstructions | | | |
| [code] | 37 | over 4 years ago | |
| LGNN: A Context-aware Line Segment Detector | | | |
| TP-LSD: Tri-Points Based Line Segment Detector | | | |
| [code] | 143 | about 5 years ago | |
| Deep Hough-Transform Line Priors | | | |
| [code] | 163 | 11 months ago | |
| Deep Hough Transform for Semantic Line Detection | | | |
| [code] | 345 | about 3 years ago | |
| Holistically-Attracted Wireframe Parsing | | | |
| [code] | 301 | over 1 year ago | |
| Learning to Reconstruct 3D Manhattan Wireframes from a Single Image | | | |
| [code] | 70 | about 1 year ago | |
| End-to-End Wireframe Parsing | | | |
| [code] | 508 | about 1 year ago | |
| PPGNet: Learning Point-Pair Graph for Line Segment Detection | | | |
| [code] | 172 | over 6 years ago | |
| Learning Attraction Field Representation for Robust Line Segment Detection | | | |
| [code] | 297 | over 6 years ago | |
| Novel Single View Constraints for Manhattan 3D Line Reconstruction | | | |
| Learning to Parse Wireframes in Images of Man-Made Environments | | | |
| [code] | 218 | about 3 years ago | |
| A Novel Linelet-Based Representation for Line Segment Detection | | | |
| MCMLSD: A Dynamic Programming Approach to Line Segment Detection | | | |
| Lifting 3D Manhattan Lines from a Single Image | | | |
| LSD: A Fast Line Segment Detector with a False Detection Control | | | |
Awesome Scene Understanding / Primitive / Outdoor Architecture |
| HEAT: Holistic Edge Attention Transformer for Structured Reconstruction | | | |
| [Project] | | | |
| Structured Outdoor Architecture Reconsruction by Exploration and Classification | | | |
| [Project] | | | |
| Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses | | | |
| [Code] | 42 | over 4 years ago | |
| Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference | | | |
| [Project] | | | |
| Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction | | | |
| [Project] | | | |
Awesome Scene Understanding / Primitive / Plane |
| MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction | | | |
| [code] | 10 | 12 months ago | |
| UniPlane: Unified Plane Detection and Reconstruction from Posed Monocular Videos | | | 📷 |
| AirPlanes: Accurate Plane Estimation via 3D-Consistent Embeddings | | | 📷 |
| [project] | | | |
| PlaneRecTR: Unified Query learning for 3D Plane Recovery from a Single View | | | |
| [Code] | 27 | about 1 year ago | |
| NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction | | | 📷 |
| [Code] | 65 | about 2 years ago | |
| PlaneFormers: From Sparse View Planes to 3D Reconstruction | | | 📷 |
| [project] | | | |
| PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos | | | 📷 |
| [Project] | | | |
| PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image | | | |
| [code] | 79 | over 3 years ago | |
| PlaneTR: Structure-Guided Transformers for 3D Plane Recovery | | | |
| [code] | 94 | over 2 years ago | |
| Planar Surface Reconstruction From Sparse Views | | | 📷 |
| [project] | | | |
| Indoor Panorama Planar 3D Reconstruction via Divide and Conquer | | | |
| [code] | 53 | about 4 years ago | |
| Learning Pairwise Inter-Plane Relations for Piecewise Planar Reconstruction | | | |
| [code] | 40 | over 4 years ago | |
| Peek-a-Boo: Occlusion Reasoning in Indoor Scenes with Plane Representations | | | |
| [project] | | | |
| Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding | | | |
| [code] | 364 | over 1 year ago | |
| PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image | | | |
| [project] | | | |
| Recovering 3D Planes from a Single Image via Convolutional Neural Networks | | | |
| [code] | 96 | over 3 years ago | |
| PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image | | | |
| [project] | | | |
Awesome Scene Understanding / Vanishing Point |
| Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction | | | |
| [code] | 101 | 12 months ago | |
| Transformer Based Line Segment Classifier with Image Context for Real-Time Vanishing Point Detection in Manhattan World | | | |
| Deep Vanishing Point Detection: Geometric Priors Make Dataset Variations Vanish | | | |
| VaPiD: A Rapid Vanishing Point Detector via Learned Optimizers | | | |
| NeurVPS: Neural Vanishing Point Scanning via Conic Convolution | | | |
| [Code] | 180 | about 1 year ago | |