# Improved Adversarial Systems for 3D Object Generation and Reconstruction

arXiv: https://arxiv.org/abs/1707.09557 · HTML: https://mlsanity.com/paper/1707.09557/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2017.

## Built on by (most cited first, 30 of 66)

- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images](https://mlsanity.com/paper/2209.11163/) (2022)
- [Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model](https://mlsanity.com/paper/2311.06214/) (2023)
- [OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation](https://mlsanity.com/paper/2301.07525/) (2023)
- [SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation](https://mlsanity.com/paper/2212.04493/) (2022)
- [Text2Tex: Text-driven Texture Synthesis via Diffusion Models](https://mlsanity.com/paper/2303.11396/) (2023)
- [GAUDI: A Neural Architect for Immersive 3D Scene Generation](https://mlsanity.com/paper/2207.13751/) (2022)
- [Neural Wavelet-domain Diffusion for 3D Shape Generation](https://mlsanity.com/paper/2209.08725/) (2022)
- [Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion](https://mlsanity.com/paper/2111.12702/) (2021)
- [HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance](https://mlsanity.com/paper/2305.18766/) (2023)
- [SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation](https://mlsanity.com/paper/2206.12055/) (2022)
- [Text-Guided Texturing by Synchronized Multi-View Diffusion](https://mlsanity.com/paper/2311.12891/) (2023)
- [UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation](https://mlsanity.com/paper/2311.01448/) (2023)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [InfiniCity: Infinite-Scale City Synthesis](https://mlsanity.com/paper/2301.09637/) (2023)
- [4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models](https://mlsanity.com/paper/2406.07472/) (2024)
- [Learning Generative Models of Textured 3D Meshes from Real-World Images](https://mlsanity.com/paper/2103.15627/) (2021)
- [DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Model](https://mlsanity.com/paper/2304.02827/) (2023)
- [SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors](https://mlsanity.com/paper/2311.17261/) (2023)
- [DiffComplete: Diffusion-based Generative 3D Shape Completion](https://mlsanity.com/paper/2306.16329/) (2023)
- [Active 3D Shape Reconstruction from Vision and Touch](https://mlsanity.com/paper/2107.09584/) (2021)
- [Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation](https://mlsanity.com/paper/2302.00190/) (2023)
- [GINA-3D: Learning to Generate Implicit Neural Assets in the Wild](https://mlsanity.com/paper/2304.02163/) (2023)
- [PhysPart: Physically Plausible Part Completion for Interactable Objects](https://mlsanity.com/paper/2408.13724/) (2024)
- [UDiFF: Generating Conditional Unsigned Distance Fields with Optimal Wavelet Diffusion](https://mlsanity.com/paper/2404.06851/) (2024)
- [Learning to Generate 3D Shapes with Generative Cellular Automata](https://mlsanity.com/paper/2103.04130/) (2021)
- [SP-GAN: Sphere-Guided 3D Shape Generation and Manipulation](https://mlsanity.com/paper/2108.04476/) (2021)
- [Interactive3D: Create What You Want by Interactive 3D Generation](https://mlsanity.com/paper/2404.16510/) (2024)
- [Building-GAN: Graph-Conditioned Architectural Volumetric Design Generation](https://mlsanity.com/paper/2104.13316/) (2021)
- [PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling](https://mlsanity.com/paper/2203.00914/) (2022)

## 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