# Equivariant Neural Rendering

arXiv: https://arxiv.org/abs/2006.07630 · HTML: https://mlsanity.com/paper/2006.07630/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2020.

## Built on by (most cited first, 30 of 48)

- [Vector Neurons: A General Framework for SO(3)-Equivariant Networks](https://mlsanity.com/paper/2104.12229/) (2021)
- [Novel View Synthesis with Diffusion Models](https://mlsanity.com/paper/2210.04628/) (2022)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [CodeNeRF: Disentangled Neural Radiance Fields for Object Categories](https://mlsanity.com/paper/2109.01750/) (2021)
- [NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion](https://mlsanity.com/paper/2302.10109/) (2023)
- [NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors](https://mlsanity.com/paper/2212.03267/) (2022)
- [GAUDI: A Neural Architect for Immersive 3D Scene Generation](https://mlsanity.com/paper/2207.13751/) (2022)
- [Unconstrained Scene Generation with Locally Conditioned Radiance Fields](https://mlsanity.com/paper/2104.00670/) (2021)
- [Vision Transformer for NeRF-Based View Synthesis from a Single Input Image](https://mlsanity.com/paper/2207.05736/) (2022)
- [ShaRF: Shape-conditioned Radiance Fields from a Single View](https://mlsanity.com/paper/2102.08860/) (2021)
- [LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation](https://mlsanity.com/paper/2403.12019/) (2024)
- [Generative Models as Distributions of Functions](https://mlsanity.com/paper/2102.04776/) (2021)
- [SHERF: Generalizable Human NeRF from a Single Image](https://mlsanity.com/paper/2303.12791/) (2023)
- [Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translation](https://mlsanity.com/paper/2202.13162/) (2022)
- [SparsePose: Sparse-View Camera Pose Regression and Refinement](https://mlsanity.com/paper/2211.16991/) (2022)
- [Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes](https://mlsanity.com/paper/2207.08656/) (2022)
- [Transframer: Arbitrary Frame Prediction with Generative Models](https://mlsanity.com/paper/2203.09494/) (2022)
- [Fast and Explicit Neural View Synthesis](https://mlsanity.com/paper/2107.05775/) (2021)
- [Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation](https://mlsanity.com/paper/2205.05922/) (2022)
- [Equivariant Representation Learning via Class-Pose Decomposition](https://mlsanity.com/paper/2207.03116/) (2022)
- [Neural Groundplans: Persistent Neural Scene Representations from a Single Image](https://mlsanity.com/paper/2207.11232/) (2022)
- [Addressing the Topological Defects of Disentanglement via Distributed Operators](https://mlsanity.com/paper/2102.05623/) (2021)
- [SymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesis](https://mlsanity.com/paper/2209.14819/) (2022)
- [Neural Fourier Transform: A General Approach to Equivariant Representation Learning](https://mlsanity.com/paper/2305.18484/) (2023)
- [Learning Generalizable Light Field Networks from Few Images](https://mlsanity.com/paper/2207.11757/) (2022)
- [On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory](https://mlsanity.com/paper/2412.11521/) (2024)
- [Unsupervised Novel View Synthesis from a Single Image](https://mlsanity.com/paper/2102.03285/) (2021)
- [InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules](https://mlsanity.com/paper/2308.13897/) (2023)
- [CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis](https://mlsanity.com/paper/2404.04913/) (2024)
- [Hamiltonian latent operators for content and motion disentanglement in image sequences](https://mlsanity.com/paper/2112.01641/) (2021)

## Abstract (arXiv)

We propose a framework for learning neural scene representations directly from images, without 3D supervision. Our key insight is that 3D structure can be imposed by ensuring that the learned representation transforms like a real 3D scene. Specifically, we introduce a loss which enforces equivariance of the scene representation with respect to 3D transformations. Our formulation allows us to infer and render scenes in real time while achieving comparable results to models requiring minutes for inference. In addition, we introduce two challenging new datasets for scene representation and neural rendering, including scenes with complex lighting and backgrounds. Through experiments, we show that our model achieves compelling results on these datasets as well as on standard ShapeNet benchmarks.