# Fast and Explicit Neural View Synthesis

arXiv: https://arxiv.org/abs/2107.05775 · HTML: https://mlsanity.com/paper/2107.05775/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 61 references that are in the map.
- First posted on arXiv 12 Jul 2021.

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations](https://mlsanity.com/paper/1906.01618/) (2019)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)
- [Neural Scene Graphs for Dynamic Scenes](https://mlsanity.com/paper/2011.10379/) (2020)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [NeX: Real-time View Synthesis with Neural Basis Expansion](https://mlsanity.com/paper/2103.05606/) (2021)
- [Stereo Magnification: Learning View Synthesis using Multiplane Images](https://mlsanity.com/paper/1805.09817/) (2018)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [Learning a Multi-View Stereo Machine](https://mlsanity.com/paper/1708.05375/) (2017)
- [Pushing the Boundaries of View Extrapolation with Multiplane Images](https://mlsanity.com/paper/1905.00413/) (2019)
- [Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs](https://mlsanity.com/paper/1703.09438/) (2017)

## Built on by (most cited first, 28 of 28)

- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [Splatter Image: Ultra-Fast Single-View 3D Reconstruction](https://mlsanity.com/paper/2312.13150/) (2023)
- [NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion](https://mlsanity.com/paper/2302.10109/) (2023)
- [GAUDI: A Neural Architect for Immersive 3D Scene Generation](https://mlsanity.com/paper/2207.13751/) (2022)
- [latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction](https://mlsanity.com/paper/2403.16292/) (2024)
- [Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data](https://mlsanity.com/paper/2306.07881/) (2023)
- [Vision Transformer for NeRF-Based View Synthesis from a Single Input Image](https://mlsanity.com/paper/2207.05736/) (2022)
- [SHERF: Generalizable Human NeRF from a Single Image](https://mlsanity.com/paper/2303.12791/) (2023)
- [Compressing Explicit Voxel Grid Representations: fast NeRFs become also small](https://mlsanity.com/paper/2210.12782/) (2022)
- [FWD: Real-time Novel View Synthesis with Forward Warping and Depth](https://mlsanity.com/paper/2206.08355/) (2022)
- [Transframer: Arbitrary Frame Prediction with Generative Models](https://mlsanity.com/paper/2203.09494/) (2022)
- [Neural Groundplans: Persistent Neural Scene Representations from a Single Image](https://mlsanity.com/paper/2207.11232/) (2022)
- [SPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images](https://mlsanity.com/paper/2212.09100/) (2022)
- [HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork](https://mlsanity.com/paper/2306.06093/) (2023)
- [SimNP: Learning Self-Similarity Priors Between Neural Points](https://mlsanity.com/paper/2309.03809/) (2023)
- [Neural Spectro-polarimetric Fields](https://mlsanity.com/paper/2306.12562/) (2023)
- [3inGAN: Learning a 3D Generative Model from Images of a Self-similar Scene](https://mlsanity.com/paper/2211.14902/) (2022)
- [A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision](https://mlsanity.com/paper/2412.00623/) (2024)
- [NeuralPassthrough: Learned Real-Time View Synthesis for VR](https://mlsanity.com/paper/2207.02186/) (2022)
- [Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors](https://mlsanity.com/paper/2411.15966/) (2024)
- [Sp2360: Sparse-view 360 Scene Reconstruction using Cascaded 2D Diffusion Priors](https://mlsanity.com/paper/2405.16517/) (2024)
- [A Pixel Is Worth More Than One 3D Gaussians in Single-View 3D Reconstruction](https://mlsanity.com/paper/2405.20310/) (2024)
- [UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images](https://mlsanity.com/paper/2410.13195/) (2024)
- [360^circ Reconstruction From a Single Image Using Space Carved Outpainting](https://mlsanity.com/paper/2309.10279/) (2023)
- [Mask-Based Modeling for Neural Radiance Fields](https://mlsanity.com/paper/2304.04962/) (2023)
- [Interpretable Single-View 3D Gaussian Splatting using Unsupervised Hierarchical Disentangled Representation Learning](https://mlsanity.com/paper/2504.04190/) (2025)
- [Depth self-supervision for single image novel view synthesis](https://mlsanity.com/paper/2308.14108/) (2023)
- [GD^2-NeRF: Generative Detail Compensation via GAN and Diffusion for One-shot Generalizable Neural Radiance Fields](https://mlsanity.com/paper/2401.00616/) (2024)

## Abstract (arXiv)

We study the problem of novel view synthesis from sparse source observations of a scene comprised of 3D objects. We propose a simple yet effective approach that is neither continuous nor implicit, challenging recent trends on view synthesis. Our approach explicitly encodes observations into a volumetric representation that enables amortized rendering. We demonstrate that although continuous radiance field representations have gained a lot of attention due to their expressive power, our simple approach obtains comparable or even better novel view reconstruction quality comparing with state-of-the-art baselines while increasing rendering speed by over 400x. Our model is trained in a category-agnostic manner and does not require scene-specific optimization. Therefore, it is able to generalize novel view synthesis to object categories not seen during training. In addition, we show that with our simple formulation, we can use view synthesis as a self-supervision signal for efficient learning of 3D geometry without explicit 3D supervision.