Scene Representation Transformer

Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

Model Overview

SRT takes few posed or unposed images of novel real-world scenes as input and produces a set-latent scene representation that is decoded to 3D videos & semantics, entirely in real-time. The model is fully geometry-free, instead powered by Transformers and attention mechanisms.

Abstract

A classical problem in computer vision is to infer a 3D scene representation from few images that can be used to render novel views at interactive rates. Previous work focuses on reconstructing pre-defined 3D representations, e.g.textured meshes, or implicit representations, e.g. radiance fields, and often requires input images with precise camera poses and long processing times for each novel scene.

In this work, we propose the Scene Representation Transformer (SRT), a method which processes posed or unposed RGB images of a new area, infers a “set-latent scene representation”, and synthesises novel views, all in a single feed-forward pass. To calculate the scene representation, we propose a generalization of the Vision Transformer to sets of images, enabling global information integration, and hence 3D reasoning. An efficient decoder transformer parameterizes the light field by attending into the scene representation to render novel views. Learning is supervised end-to-end by minimizing a novel-view reconstruction error.

We show that this method outperforms recent baselines in terms of PSNR and speed on synthetic datasets, including a new dataset created for the paper. Further, we demonstrate that SRT scales to support interactive visualization and semantic segmentation of real-world outdoor environments using Street View imagery.

Citation

@article{srt_arxiv, title={{Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations}}, author={Mehdi S. M. Sajjadi and Henning Meyer and Etienne Pot and Urs Bergmann and Klaus Greff and Noha Radwan and Suhani Vora and Mario Lucic and Daniel Duckworth and Alexey Dosovitskiy and Jakob Uszkoreit and Thomas Funkhouser and Andrea Tagliasacchi}, journal={arXiv preprint arXiv:2111.13152}, url={https://arxiv.org/abs/arXiv:2111.13152}, year={2021} }