mlsanityData to 7 Oct 2026

Improved Adversarial Systems for 3D Object Generation and Reconstruction

arXiv 1707.09557 ↗First posted 29 Jul 2017cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3D shape of objects. While GANs have been used in this domain previously, they are notoriously hard to train, especially for the complex joint data distribution over 3D objects of many categories and orientations. Our method extends previous work by employing the Wasserstein distance normalized with gradient penalization as a training objective. This enables improved generation from the joint object shape distribution. Our system can also reconstruct 3D shape from 2D images and perform shape completion from occluded 2.5D range scans. We achieve notable quantitative improvements in comparison to existing baselines

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 13; 2023: 21; 2024: 15; 2025: 2; 2026: 5.

66 papers.

Sort:

By area:

  1. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  2. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  3. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  4. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  5. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 287
  6. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  7. 2022GAUDI: A Neural Architect for Immersive 3D Scene Generationcited by 136
  8. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  9. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 111
  10. 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidancecited by 109
  11. 2022SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generationcited by 92
  12. 2023Text-Guided Texturing by Synchronized Multi-View Diffusioncited by 86
38 more
  1. 2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 76
  2. 20213D Semantic Scene Completion: a Surveycited by 74
  3. 2023InfiniCity: Infinite-Scale City Synthesiscited by 68
  4. 20244Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Modelscited by 64
  5. 2021Learning Generative Models of Textured 3D Meshes from Real-World Imagescited by 44
  6. 2023DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Modelcited by 43
  7. 2023SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priorscited by 43
  8. 2023DiffComplete: Diffusion-based Generative 3D Shape Completioncited by 35
  9. 2021Active 3D Shape Reconstruction from Vision and Touchcited by 34
  10. 2023Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulationcited by 27
  11. 2023GINA-3D: Learning to Generate Implicit Neural Assets in the Wildcited by 25
  12. 2024PhysPart: Physically Plausible Part Completion for Interactable Objectscited by 24
  13. 2024UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusioncited by 23
  14. 2021Learning to Generate 3D Shapes with Generative Cellular Automatacited by 22
  15. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  16. 2024Interactive3D: Create What You Want by Interactive 3D Generationcited by 21
  17. 2021Building-GAN: Graph-Conditioned Architectural Volumetric Design Generationcited by 20
  18. 2022PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsamplingcited by 18
  19. 2024AToM: Amortized Text-to-Mesh using 2D Diffusioncited by 18
  20. 20213DRIMR: 3D Reconstruction and Imaging via mmWave Radar based on Deep Learningcited by 16
  21. 2023EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generationcited by 16
  22. 2023Adversarial Score Distillation: When score distillation meets GANcited by 15
  23. 20233D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detectioncited by 15
  24. 2023CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Explorationcited by 9
  25. 2021Unsupervised Shape Completion via Deep Prior in the Neural Tangent Kernel Perspectivecited by 8
  26. 2022Probabilistic Implicit Scene Completioncited by 8
  27. 2022Monocular 3D Object Reconstruction with GAN Inversioncited by 8
  28. 2022GARNet: Global-Aware Multi-View 3D Reconstruction Network and the Cost-Performance Tradeoffcited by 8
  29. 2023Vision + Language Applications: A Surveycited by 8
  30. 2023Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Modelscited by 8
  31. 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimizationcited by 8
  32. 2024DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priorscited by 8
  33. 2022R2P: A Deep Learning Model from mmWave Radar to Point Cloudcited by 7
  34. 2023UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstructioncited by 7
  35. 2022DeepMend: Learning Occupancy Functions to Represent Shape for Repaircited by 6
  36. 2024MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assetscited by 6
  37. 2021DeepPoint: A Deep Learning Model for 3D Reconstruction in Point Clouds via mmWave Radarcited by 5
  38. 2022DeepJoin: Learning a Joint Occupancy, Signed Distance, and Normal Field Function for Shape Repaircited by 5

50 most cited of 66 All 66 (JSON)