mlsanityData to 7 Oct 2026

Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes

arXiv 2207.08656 ↗First posted 18 Jul 2022cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

We present a new framework to reconstruct holistic 3D indoor scenes including both room background and indoor objects from single-view images. Existing methods can only produce 3D shapes of indoor objects with limited geometry quality because of the heavy occlusion of indoor scenes. To solve this, we propose an instance-aligned implicit function (InstPIFu) for detailed object reconstruction. Combining with instance-aligned attention module, our method is empowered to decouple mixed local features toward the occluded instances. Additionally, unlike previous methods that simply represents the room background as a 3D bounding box, depth map or a set of planes, we recover the fine geometry of the background via implicit representation. Extensive experiments on the SUN RGB-D, Pix3D, 3D-FUTURE, and 3D-FRONT datasets demonstrate that our method outperforms existing approaches in both background and foreground object reconstruction. Our code and model will be made publicly available.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 49 of its 58 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

49 of 58 references.

References · 49

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2017Mask R-CNNcited by 7,259
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  6. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  9. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  10. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  11. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  12. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
37 more
  1. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  2. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  3. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  4. 2017Neural 3D Mesh Renderercited by 437
  5. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 375
  6. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  7. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  8. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  9. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  10. 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
  11. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  12. 2020Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Imagecited by 170
  13. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  14. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  15. 2018PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Imagecited by 105
  16. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  17. 2018LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Imagecited by 94
  18. 2021Holistic 3D Scene Understanding from a Single Image with Implicit Representationcited by 94
  19. 2016IM2CADcited by 78
  20. 2019Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsensecited by 71
  21. 2018Holistic 3D Scene Parsing and Reconstruction from a Single RGB Imagecited by 69
  22. 2019Learning to Infer and Execute 3D Shape Programscited by 68
  23. 2019Deep Level Sets: Implicit Surface Representations for 3D Shape Inferencecited by 52
  24. 2018Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimationcited by 51
  25. 2017Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scenecited by 50
  26. 2020Equivariant Neural Renderingcited by 47
  27. 2019A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Imagescited by 37
  28. 20193D-RelNet: Joint Object and Relational Network for 3D Predictioncited by 28
  29. 2017DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Imagecited by 25
  30. 2018Adaptive O-CNN: A Patch-based Deep Representation of 3D Shapescited by 25
  31. 2019Few-Shot Generalization for Single-Image 3D Reconstruction via Priorscited by 25
  32. 2020General 3D Room Layout from a Single View by Render-and-Comparecited by 21
  33. 2016A Coarse-to-Fine Indoor Layout Estimation (CFILE) Methodcited by 15
  34. 20183D-PSRNet: Part Segmented 3D Point Cloud Reconstruction From a Single Imagecited by 12
  35. 2018CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervisioncited by 12
  36. 2021Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Imagecited by 7
  37. 2017SeeThrough: Finding Chairs in Heavily Occluded Indoor Scene Imagescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 6; 2024: 12; 2025: 9; 2026: 14.

43 papers.

Sort:

By area:

  1. 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 113
  2. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 101
  3. 2024Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single Viewcited by 59
  4. 2023DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Imagecited by 48
  5. 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 44
  6. 2023Single-view 3D Scene Reconstruction with High-fidelity Shape and Texturecited by 37
  7. 2025Decompositional Neural Scene Reconstruction with Generative Diffusion Priorcited by 30
  8. 2022Learning 3D Scene Priors with 2D Supervisioncited by 24
  9. 2025DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusioncited by 23
  10. 2023PanoContext-Former: Panoramic Total Scene Understanding with a Transformercited by 19
  11. 2026ShapeR: Robust Conditional 3D Shape Generation from Casual Capturescited by 19
  12. 2025SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Modelcited by 15
31 more
  1. 2024Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modelingcited by 10
  2. 20253D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Frameworkcited by 10
  3. 20263D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Imagecited by 9
  4. 2024Coherent 3D Scene Diffusion From a Single RGB Imagecited by 8
  5. 2024Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wildcited by 7
  6. 2024Unsupervised Template-assisted Point Cloud Shape Correspondence Networkcited by 7
  7. 2024Reconstructing Animals and the Wildcited by 7
  8. 2025Digital Twin Generation from Visual Data: A Surveycited by 7
  9. 2023Convex Decomposition of Indoor Scenescited by 6
  10. 2023LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Datasetcited by 5
  11. 2023Blocks2World: Controlling Realistic Scenes with Editable Primitivescited by 4
  12. 2025GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherencecited by 4
  13. 2024Robust Shape Fitting for 3D Scene Abstractioncited by 3
  14. 2024M3D: Dual-Stream Selective State Spaces and Depth-Driven Framework for High-Fidelity Single-View 3D Reconstructioncited by 3
  15. 2026PixARMesh: Autoregressive Mesh-Native Single-View Scene Reconstructioncited by 3
  16. 2026AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environmentscited by 3
  17. 2025Generative Blocks World: Moving Things Around in Picturescited by 2
  18. 2026WorldSculpt: Generating Compositional Worlds from Grounded Videoscited by 2
  19. 2024MeTTA: Single-View to 3D Textured Mesh Reconstruction with Test-Time Adaptationcited by 1
  20. 2026Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Imagecited by 1
  21. 2026JRM: Joint Reconstruction Model for Multiple Objects without Alignmentcited by 1
  22. 2022Review on 6D Object Pose Estimation with the focus on Indoor Scene Understandingcited by 0
  23. 2024Improved Convex Decomposition with Ensembling and Negative Primitivescited by 0
  24. 2025CC-FMO: Camera-Conditioned Zero-Shot Single Image to 3D Scene Generation with Foundation Model Orchestrationcited by 0
  25. 2026MGP-KAD: Multimodal Geometric Priors and Kolmogorov-Arnold Decoder for Single-View 3D Reconstruction in Complex Scenescited by 0
  26. 2026TIMI: Training-Free Image-to-3D Multi-Instance Generation with Spatial Fidelitycited by 0
  27. 2026DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusioncited by 0
  28. 2026HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generationcited by 0
  29. 2026SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenescited by 0
  30. 2026Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstructioncited by 0
  31. 2026Collision-Aware and Observation-Aligned Object-Centric Scene Reconstruction from Point Cloudcited by 0