mlsanityData to 14 Oct 2026

Floating No More: Object-Ground Reconstruction from a Single Image

arXiv 2407.18914 ↗First posted 26 Jul 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Recent advancements in 3D object reconstruction from single images have primarily focused on improving the accuracy of object shapes. Yet, these techniques often fail to accurately capture the inter-relation between the object, ground, and camera. As a result, the reconstructed objects often appear floating or tilted when placed on flat surfaces. This limitation significantly affects 3D-aware image editing applications like shadow rendering and object pose manipulation. To address this issue, we introduce ORG (Object Reconstruction with Ground), a novel task aimed at reconstructing 3D object geometry in conjunction with the ground surface. Our method uses two compact pixel-level representations to depict the relationship between camera, object, and ground. Experiments show that the proposed ORG model can effectively reconstruct object-ground geometry on unseen data, significantly enhancing the quality of shadow generation and pose manipulation compared to conventional single-image 3D reconstruction techniques.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 52 of its 62 references that are in the map. First posted on arXiv 26 Jul 2024.

Builds on

52 of 62 references.

References · 52

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  5. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  6. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  7. 2021Vision Transformers for Dense Predictioncited by 1,803
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  9. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  10. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
38 more
  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  2. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  3. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  4. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  5. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  6. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
  7. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  8. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  9. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  10. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  11. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  12. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  13. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 343
  14. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  15. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  16. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  17. 2019Enforcing geometric constraints of virtual normal for depth predictioncited by 234
  18. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 216
  19. 2016Single-Image Depth Perception in the Wildcited by 180
  20. 2023MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimationcited by 174
  21. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  22. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  23. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  24. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  25. 2020Shape and Viewpoint without Keypointscited by 92
  26. 2022What's in your hands? 3D Reconstruction of Generic Objects in Handscited by 90
  27. 2022Perspective Fields for Single Image Camera Calibrationcited by 75
  28. 2019Web Stereo Video Supervision for Depth Prediction from Dynamic Scenescited by 73
  29. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  30. 2018Learning Shape Priors for Single-View 3D Completion and Reconstructioncited by 68
  31. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  32. 2020OASIS: A Large-Scale Dataset for Single Image 3D in the Wildcited by 62
  33. 2014Category-Specific Object Reconstruction from a Single Imagecited by 56
  34. 2017A Perceptual Measure for Deep Single Image Camera Calibrationcited by 45
  35. 2023NDDepth: Normal-Distance Assisted Monocular Depth Estimationcited by 45
  36. 2021CTRL-C: Camera calibration TRansformer with Line-Classificationcited by 33
  37. 2019UprightNet: Geometry-Aware Camera Orientation Estimation from Single Imagescited by 26
  38. 2018Learning Single-Image Depth from Videos using Quality Assessment Networkscited by 25

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024SceneCraft: Layout-Guided 3D Scene Generationcited by 41
  2. 2025Generative AI for Cel-Animation: A Surveycited by 17
  3. 2025Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimationcited by 1