# Geometry-Aware Neural Rendering

arXiv: https://arxiv.org/abs/1911.04554 · HTML: https://mlsanity.com/paper/1911.04554/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 10 of 10)

- [ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers](https://mlsanity.com/paper/2203.10157/) (2022)
- [MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions](https://mlsanity.com/paper/2104.13325/) (2021)
- [Learning a State Representation and Navigation in Cluttered and Dynamic Environments](https://mlsanity.com/paper/2103.04351/) (2021)
- [Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views](https://mlsanity.com/paper/2111.07117/) (2021)
- [Transframer: Arbitrary Frame Prediction with Generative Models](https://mlsanity.com/paper/2203.09494/) (2022)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [STR-GQN: Scene Representation and Rendering for Unknown Cameras Based on Spatial Transformation Routing](https://mlsanity.com/paper/2108.03072/) (2021)
- [Pose-guided Generative Adversarial Net for Novel View Action Synthesis](https://mlsanity.com/paper/2110.07993/) (2021)
- [SatDreamer360: Multiview-Consistent Generation of Ground-Level Scenes from Satellite Imagery](https://mlsanity.com/paper/2506.00600/) (2025)
- [Identifiable Object Representations under Spatial Ambiguities](https://mlsanity.com/paper/2506.07806/) (2025)

## Abstract (arXiv)

Understanding the 3-dimensional structure of the world is a core challenge in computer vision and robotics. Neural rendering approaches learn an implicit 3D model by predicting what a camera would see from an arbitrary viewpoint. We extend existing neural rendering to more complex, higher dimensional scenes than previously possible. We propose Epipolar Cross Attention (ECA), an attention mechanism that leverages the geometry of the scene to perform efficient non-local operations, requiring only O(n) comparisons per spatial dimension instead of O(n2). We introduce three new simulated datasets inspired by real-world robotics and demonstrate that ECA significantly improves the quantitative and qualitative performance of Generative Query Networks (GQN).