# Geometry-Free View Synthesis: Transformers and no 3D Priors

arXiv: https://arxiv.org/abs/2104.07652 · HTML: https://mlsanity.com/paper/2104.07652/

## Key facts

- Cited by 100 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 84 references that are in the map.
- First posted on arXiv 15 Apr 2021.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Jukebox: A Generative Model for Music](https://mlsanity.com/paper/2005.00341/) (2020)
- [PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications](https://mlsanity.com/paper/1701.05517/) (2017)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)
- [A note on the evaluation of generative models](https://mlsanity.com/paper/1511.01844/) (2015)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Single-View View Synthesis with Multiplane Images](https://mlsanity.com/paper/2004.11364/) (2020)
- [DeepView: View Synthesis with Learned Gradient Descent](https://mlsanity.com/paper/1906.07316/) (2019)
- [Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image](https://mlsanity.com/paper/2012.09855/) (2020)
- [Free View Synthesis](https://mlsanity.com/paper/2008.05511/) (2020)
- [A Decomposable Attention Model for Natural Language Inference](https://mlsanity.com/paper/1606.01933/) (2016)
- [3D Photography using Context-aware Layered Depth Inpainting](https://mlsanity.com/paper/2004.04727/) (2020)
- [Diagnosing and Enhancing VAE Models](https://mlsanity.com/paper/1903.05789/) (2019)
- [Pushing the Boundaries of View Extrapolation with Multiplane Images](https://mlsanity.com/paper/1905.00413/) (2019)

## Built on by (most cited first, 30 of 100)

- [Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives](https://mlsanity.com/paper/2311.18259/) (2023)
- [ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis](https://mlsanity.com/paper/2409.02048/) (2024)
- [Generative Novel View Synthesis with 3D-Aware Diffusion Models](https://mlsanity.com/paper/2304.02602/) (2023)
- [Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations](https://mlsanity.com/paper/2111.13152/) (2021)
- [SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction](https://mlsanity.com/paper/2212.00792/) (2022)
- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion](https://mlsanity.com/paper/2302.10109/) (2023)
- [SceneScape: Text-Driven Consistent Scene Generation](https://mlsanity.com/paper/2302.01133/) (2023)
- [GAUDI: A Neural Architect for Immersive 3D Scene Generation](https://mlsanity.com/paper/2207.13751/) (2022)
- [Generalizable Patch-Based Neural Rendering](https://mlsanity.com/paper/2207.10662/) (2022)
- [latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction](https://mlsanity.com/paper/2403.16292/) (2024)
- [Consistent View Synthesis with Pose-Guided Diffusion Models](https://mlsanity.com/paper/2303.17598/) (2023)
- [Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image](https://mlsanity.com/paper/2406.04343/) (2024)
- [VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory](https://mlsanity.com/paper/2506.18903/) (2025)
- [Light Field Neural Rendering](https://mlsanity.com/paper/2112.09687/) (2021)
- [Street-View Image Generation from a Bird's-Eye View Layout](https://mlsanity.com/paper/2301.04634/) (2023)
- [MEt3R: Measuring Multi-View Consistency in Generated Images](https://mlsanity.com/paper/2501.06336/) (2025)
- [Object Scene Representation Transformer](https://mlsanity.com/paper/2206.06922/) (2022)
- [Consistent123: Improve Consistency for One Image to 3D Object Synthesis](https://mlsanity.com/paper/2310.08092/) (2023)
- [PixelSynth: Generating a 3D-Consistent Experience from a Single Image](https://mlsanity.com/paper/2108.05892/) (2021)
- [InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images](https://mlsanity.com/paper/2207.11148/) (2022)
- [NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer](https://mlsanity.com/paper/2405.15364/) (2024)
- [NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models](https://mlsanity.com/paper/2304.09787/) (2023)
- [Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models](https://mlsanity.com/paper/2304.10700/) (2023)
- [GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping](https://mlsanity.com/paper/2405.17251/) (2024)
- [MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes](https://mlsanity.com/paper/2405.14475/) (2024)
- [ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers](https://mlsanity.com/paper/2203.10157/) (2022)
- [MultiDiff: Consistent Novel View Synthesis from a Single Image](https://mlsanity.com/paper/2406.18524/) (2024)
- [Real-Time Radiance Fields for Single-Image Portrait View Synthesis](https://mlsanity.com/paper/2305.02310/) (2023)
- [Advances in 3D Generation: A Survey](https://mlsanity.com/paper/2401.17807/) (2024)

## Abstract (arXiv)

Is a geometric model required to synthesize novel views from a single image? Being bound to local convolutions, CNNs need explicit 3D biases to model geometric transformations. In contrast, we demonstrate that a transformer-based model can synthesize entirely novel views without any hand-engineered 3D biases. This is achieved by (i) a global attention mechanism for implicitly learning long-range 3D correspondences between source and target views, and (ii) a probabilistic formulation necessary to capture the ambiguity inherent in predicting novel views from a single image, thereby overcoming the limitations of previous approaches that are restricted to relatively small viewpoint changes. We evaluate various ways to integrate 3D priors into a transformer architecture. However, our experiments show that no such geometric priors are required and that the transformer is capable of implicitly learning 3D relationships between images. Furthermore, this approach outperforms the state of the art in terms of visual quality while covering the full distribution of possible realizations. Code is available at https://git.io/JOnwn