# Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering

arXiv: https://arxiv.org/abs/2010.09125 · HTML: https://mlsanity.com/paper/2010.09125/

## Key facts

- Cited by 101 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2020.

## Built on by (most cited first, 30 of 101)

- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction](https://mlsanity.com/paper/2109.00512/) (2021)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://mlsanity.com/paper/2210.06978/) (2022)
- [GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images](https://mlsanity.com/paper/2209.11163/) (2022)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation](https://mlsanity.com/paper/2112.11427/) (2021)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort](https://mlsanity.com/paper/2104.06490/) (2021)
- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising](https://mlsanity.com/paper/2206.03380/) (2022)
- [DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models](https://mlsanity.com/paper/2303.11681/) (2023)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models](https://mlsanity.com/paper/2304.00916/) (2023)
- [Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization](https://mlsanity.com/paper/2104.05833/) (2021)
- [VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids](https://mlsanity.com/paper/2206.07695/) (2022)
- [Generative Models as a Data Source for Multiview Representation Learning](https://mlsanity.com/paper/2106.05258/) (2021)
- [gradSim: Differentiable simulation for system identification and visuomotor control](https://mlsanity.com/paper/2104.02646/) (2021)
- [GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds](https://mlsanity.com/paper/2104.07659/) (2021)
- [SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections](https://mlsanity.com/paper/2205.15768/) (2022)
- [TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models](https://mlsanity.com/paper/2310.13772/) (2023)
- [TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition](https://mlsanity.com/paper/2210.11277/) (2022)
- [NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models](https://mlsanity.com/paper/2304.09787/) (2023)
- [GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving](https://mlsanity.com/paper/2101.06543/) (2021)
- [Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translation](https://mlsanity.com/paper/2202.13162/) (2022)
- [Adaptive Shells for Efficient Neural Radiance Field Rendering](https://mlsanity.com/paper/2311.10091/) (2023)
- [Unsupervised Learning of 3D Object Categories from Videos in the Wild](https://mlsanity.com/paper/2103.16552/) (2021)
- [GAN-Supervised Dense Visual Alignment](https://mlsanity.com/paper/2112.05143/) (2021)
- [DOVE: Learning Deformable 3D Objects by Watching Videos](https://mlsanity.com/paper/2107.10844/) (2021)

## Abstract (arXiv)

Differentiable rendering has paved the way to training neural networks to perform "inverse graphics" tasks such as predicting 3D geometry from monocular photographs. To train high performing models, most of the current approaches rely on multi-view imagery which are not readily available in practice. Recent Generative Adversarial Networks (GANs) that synthesize images, in contrast, seem to acquire 3D knowledge implicitly during training: object viewpoints can be manipulated by simply manipulating the latent codes. However, these latent codes often lack further physical interpretation and thus GANs cannot easily be inverted to perform explicit 3D reasoning. In this paper, we aim to extract and disentangle 3D knowledge learned by generative models by utilizing differentiable renderers. Key to our approach is to exploit GANs as a multi-view data generator to train an inverse graphics network using an off-the-shelf differentiable renderer, and the trained inverse graphics network as a teacher to disentangle the GAN's latent code into interpretable 3D properties. The entire architecture is trained iteratively using cycle consistency losses. We show that our approach significantly outperforms state-of-the-art inverse graphics networks trained on existing datasets, both quantitatively and via user studies. We further showcase the disentangled GAN as a controllable 3D "neural renderer", complementing traditional graphics renderers.