# 3D generation on ImageNet

arXiv: https://arxiv.org/abs/2303.01416 · HTML: https://mlsanity.com/paper/2303.01416/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 80 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 30 of 60)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets](https://mlsanity.com/paper/2202.00273/) (2022)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields](https://mlsanity.com/paper/2112.05139/) (2021)

## Built on by (most cited first, 30 of 47)

- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [SyncDreamer: Generating Multiview-consistent Images from a Single-view Image](https://mlsanity.com/paper/2309.03453/) (2023)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [Text2Tex: Text-driven Texture Synthesis via Diffusion Models](https://mlsanity.com/paper/2303.11396/) (2023)
- [DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model](https://mlsanity.com/paper/2311.09217/) (2023)
- [DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior](https://mlsanity.com/paper/2310.16818/) (2023)
- [ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image](https://mlsanity.com/paper/2310.17994/) (2023)
- [Consistent123: Improve Consistency for One Image to 3D Object Synthesis](https://mlsanity.com/paper/2310.08092/) (2023)
- [3D-aware Image Generation using 2D Diffusion Models](https://mlsanity.com/paper/2303.17905/) (2023)
- [Real-Time Radiance Fields for Single-Image Portrait View Synthesis](https://mlsanity.com/paper/2305.02310/) (2023)
- [SPAD : Spatially Aware Multiview Diffusers](https://mlsanity.com/paper/2402.05235/) (2024)
- [Gaussian Shell Maps for Efficient 3D Human Generation](https://mlsanity.com/paper/2311.17857/) (2023)
- [CC3D: Layout-Conditioned Generation of Compositional 3D Scenes](https://mlsanity.com/paper/2303.12074/) (2023)
- [SceneWiz3D: Towards Text-guided 3D Scene Composition](https://mlsanity.com/paper/2312.08885/) (2023)
- [AutoDecoding Latent 3D Diffusion Models](https://mlsanity.com/paper/2307.05445/) (2023)
- [SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors](https://mlsanity.com/paper/2311.17261/) (2023)
- [Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis](https://mlsanity.com/paper/2507.23785/) (2025)
- [GINA-3D: Learning to Generate Implicit Neural Assets in the Wild](https://mlsanity.com/paper/2304.02163/) (2023)
- [Real3D: Scaling Up Large Reconstruction Models with Real-World Images](https://mlsanity.com/paper/2406.08479/) (2024)
- [NViST: In the Wild New View Synthesis from a Single Image with Transformers](https://mlsanity.com/paper/2312.08568/) (2023)
- [CAD: Photorealistic 3D Generation via Adversarial Distillation](https://mlsanity.com/paper/2312.06663/) (2023)
- [AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image Collections](https://mlsanity.com/paper/2309.02186/) (2023)
- [AI-Generated Images as Data Source: The Dawn of Synthetic Era](https://mlsanity.com/paper/2310.01830/) (2023)
- [Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields](https://mlsanity.com/paper/2402.14196/) (2024)
- [What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs](https://mlsanity.com/paper/2401.02411/) (2024)
- [Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion](https://mlsanity.com/paper/2503.22262/) (2025)
- [WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space](https://mlsanity.com/paper/2311.13570/) (2023)
- [VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation](https://mlsanity.com/paper/2604.02580/) (2026)
- [PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds](https://mlsanity.com/paper/2311.04501/) (2023)
- [Boosting3D: High-Fidelity Image-to-3D by Boosting 2D Diffusion Prior to 3D Prior with Progressive Learning](https://mlsanity.com/paper/2311.13617/) (2023)

## Abstract (arXiv)

Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the scene. This makes them inapplicable to diverse, in-the-wild datasets of non-alignable scenes rendered from arbitrary camera poses. In this work, we develop a 3D generator with Generic Priors (3DGP): a 3D synthesis framework with more general assumptions about the training data, and show that it scales to very challenging datasets, like ImageNet. Our model is based on three new ideas. First, we incorporate an inaccurate off-the-shelf depth estimator into 3D GAN training via a special depth adaptation module to handle the imprecision. Then, we create a flexible camera model and a regularization strategy for it to learn its distribution parameters during training. Finally, we extend the recent ideas of transferring knowledge from pre-trained classifiers into GANs for patch-wise trained models by employing a simple distillation-based technique on top of the discriminator. It achieves more stable training than the existing methods and speeds up the convergence by at least 40%. We explore our model on four datasets: SDIP Dogs 256x256, SDIP Elephants 256x256, LSUN Horses 256x256, and ImageNet 256x256, and demonstrate that 3DGP outperforms the recent state-of-the-art in terms of both texture and geometry quality. Code and visualizations: https://snap-research.github.io/3dgp.