# RenderNet: A deep convolutional network for differentiable rendering from 3D shapes

arXiv: https://arxiv.org/abs/1806.06575 · HTML: https://mlsanity.com/paper/1806.06575/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2018.

## Built on by (most cited first, 30 of 42)

- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering](https://mlsanity.com/paper/2106.02634/) (2021)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation](https://mlsanity.com/paper/2112.08867/) (2021)
- [GNeRF: GAN-based Neural Radiance Field without Posed Camera](https://mlsanity.com/paper/2103.15606/) (2021)
- [3D Neural Scene Representations for Visuomotor Control](https://mlsanity.com/paper/2107.04004/) (2021)
- [Learning to Render Novel Views from Wide-Baseline Stereo Pairs](https://mlsanity.com/paper/2304.08463/) (2023)
- [gradSim: Differentiable simulation for system identification and visuomotor control](https://mlsanity.com/paper/2104.02646/) (2021)
- [PVA: Pixel-aligned Volumetric Avatars](https://mlsanity.com/paper/2101.02697/) (2021)
- [FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow](https://mlsanity.com/paper/2306.00180/) (2023)
- [NeuroFluid: Fluid Dynamics Grounding with Particle-Driven Neural Radiance Fields](https://mlsanity.com/paper/2203.01762/) (2022)
- [Dynamic Neural Garments](https://mlsanity.com/paper/2102.11811/) (2021)
- [RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination](https://mlsanity.com/paper/2505.21925/) (2025)
- [Representing 3D Shapes with Probabilistic Directed Distance Fields](https://mlsanity.com/paper/2112.05300/) (2021)
- [Splatting-based Synthesis for Video Frame Interpolation](https://mlsanity.com/paper/2201.10075/) (2022)
- [Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future](https://mlsanity.com/paper/2108.04543/) (2021)
- [3D-Aware Video Generation](https://mlsanity.com/paper/2206.14797/) (2022)
- [MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models](https://mlsanity.com/paper/2505.15185/) (2025)
- [Generative Modeling for Multi-task Visual Learning](https://mlsanity.com/paper/2106.13409/) (2021)
- [SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field](https://mlsanity.com/paper/2312.08692/) (2023)
- [Shadow Art Revisited: A Differentiable Rendering Based Approach](https://mlsanity.com/paper/2107.14539/) (2021)
- [ADOP: Approximate Differentiable One-Pixel Point Rendering](https://mlsanity.com/paper/2110.06635/) (2021)
- [DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimation](https://mlsanity.com/paper/2112.08775/) (2021)
- [Multi-View Reconstruction using Signed Ray Distance Functions (SRDF)](https://mlsanity.com/paper/2209.00082/) (2022)
- [Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors](https://mlsanity.com/paper/2104.11101/) (2021)
- [Controllable Radiance Fields for Dynamic Face Synthesis](https://mlsanity.com/paper/2210.05825/) (2022)
- [An Effective Loss Function for Generating 3D Models from Single 2D Image without Rendering](https://mlsanity.com/paper/2103.03390/) (2021)
- [Solving Inverse Problems with NerfGANs](https://mlsanity.com/paper/2112.09061/) (2021)
- [PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis](https://mlsanity.com/paper/2202.04879/) (2022)
- [End-to-end View Synthesis via NeRF Attention](https://mlsanity.com/paper/2207.14741/) (2022)

## Abstract (arXiv)

Traditional computer graphics rendering pipeline is designed for procedurally generating 2D quality images from 3D shapes with high performance. The non-differentiability due to discrete operations such as visibility computation makes it hard to explicitly correlate rendering parameters and the resulting image, posing a significant challenge for inverse rendering tasks. Recent work on differentiable rendering achieves differentiability either by designing surrogate gradients for non-differentiable operations or via an approximate but differentiable renderer. These methods, however, are still limited when it comes to handling occlusion, and restricted to particular rendering effects. We present RenderNet, a differentiable rendering convolutional network with a novel projection unit that can render 2D images from 3D shapes. Spatial occlusion and shading calculation are automatically encoded in the network. Our experiments show that RenderNet can successfully learn to implement different shaders, and can be used in inverse rendering tasks to estimate shape, pose, lighting and texture from a single image.