mlsanityData to 7 Oct 2026

Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild

arXiv 2403.14539 ↗First posted 21 Mar 2024cs.CV cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent monocular 3D shape reconstruction methods have shown promising zero-shot results on object-segmented images without any occlusions. However, their effectiveness is significantly compromised in real-world conditions, due to imperfect object segmentation by off-the-shelf models and the prevalence of occlusions. To effectively address these issues, we propose a unified regression model that integrates segmentation and reconstruction, specifically designed for occlusion-aware 3D shape reconstruction. To facilitate its reconstruction in the wild, we also introduce a scalable data synthesis pipeline that simulates a wide range of variations in objects, occluders, and backgrounds. Training on our synthetic data enables the proposed model to achieve state-of-the-art zero-shot results on real-world images, using significantly fewer parameters than competing approaches.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 86 of its 104 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

86 of 104 references.

References · 86

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2023Segment Anythingcited by 8,158
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  9. 2022Scalable Diffusion Models with Transformerscited by 5,931
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  11. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  12. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
38 more
  1. 2020Extracting Training Data from Large Language Modelscited by 2,144
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  4. 2021Vision Transformers for Dense Predictioncited by 1,789
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  7. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  8. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  9. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  10. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  11. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  12. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  13. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  14. 2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
  15. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  16. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  17. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  18. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  19. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  20. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  21. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  22. 2021Domain Generalization with MixStylecited by 563
  23. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  24. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  25. 2023LLaMA-VID: An Image is Worth 2 Tokens in Large Language Modelscited by 539
  26. 2023Erasing Concepts from Diffusion Modelscited by 530
  27. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  28. 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
  29. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  30. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 339
  31. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  32. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  33. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  34. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
  35. 2019Episodic Training for Domain Generalizationcited by 245
  36. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 245
  37. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  38. 2020Domain Generalization using Causal Matchingcited by 224

50 most cited of 86 All 86 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
  2. 2025SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Modelcited by 15
  3. 2024Monocular Human-Object Reconstruction in the Wildcited by 9
  4. 2025Asset-Driven Sematic Reconstruction of Dynamic Scene with Multi-Human-Object Interactionscited by 0
  5. 2026Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touchcited by 0
  6. 2026Point-MF: Stabilizing One-Step Mean Flows for Single-Image Point Cloud Reconstructioncited by 0
  7. 2026Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Part123: Part-aware 3D Reconstruction from a Single-view Image
  2. 2026ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
  3. 2024Zero-Shot Multi-Object Scene Completion
  4. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images
  5. 2023Anything-3D: Towards Single-view Anything Reconstruction in the Wild
  6. 2025ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing
  7. 2023Zero-Shot 3D Shape Correspondence
  8. 2025Zero-P-to-3: Zero-Shot Partial-View Images to 3D Object