Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Boyang, Tucker, Richard, Li, Zhengqi, Guibas, Leonidas, Snavely, Noah, Wetzstein, Gordon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917733338185728
author Deng, Boyang
Tucker, Richard
Li, Zhengqi
Guibas, Leonidas
Snavely, Noah
Wetzstein, Gordon
author_facet Deng, Boyang
Tucker, Richard
Li, Zhengqi
Guibas, Leonidas
Snavely, Noah
Wetzstein, Gordon
contents We present a method for generating Streetscapes-long sequences of views through an on-the-fly synthesized city-scale scene. Our generation is conditioned by language input (e.g., city name, weather), as well as an underlying map/layout hosting the desired trajectory. Compared to recent models for video generation or 3D view synthesis, our method can scale to much longer-range camera trajectories, spanning several city blocks, while maintaining visual quality and consistency. To achieve this goal, we build on recent work on video diffusion, used within an autoregressive framework that can easily scale to long sequences. In particular, we introduce a new temporal imputation method that prevents our autoregressive approach from drifting from the distribution of realistic city imagery. We train our Streetscapes system on a compelling source of data-posed imagery from Google Street View, along with contextual map data-which allows users to generate city views conditioned on any desired city layout, with controllable camera poses. Please see more results at our project page at https://boyangdeng.com/streetscapes.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13759
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
Deng, Boyang
Tucker, Richard
Li, Zhengqi
Guibas, Leonidas
Snavely, Noah
Wetzstein, Gordon
Computer Vision and Pattern Recognition
Graphics
We present a method for generating Streetscapes-long sequences of views through an on-the-fly synthesized city-scale scene. Our generation is conditioned by language input (e.g., city name, weather), as well as an underlying map/layout hosting the desired trajectory. Compared to recent models for video generation or 3D view synthesis, our method can scale to much longer-range camera trajectories, spanning several city blocks, while maintaining visual quality and consistency. To achieve this goal, we build on recent work on video diffusion, used within an autoregressive framework that can easily scale to long sequences. In particular, we introduce a new temporal imputation method that prevents our autoregressive approach from drifting from the distribution of realistic city imagery. We train our Streetscapes system on a compelling source of data-posed imagery from Google Street View, along with contextual map data-which allows users to generate city views conditioned on any desired city layout, with controllable camera poses. Please see more results at our project page at https://boyangdeng.com/streetscapes.
title Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2407.13759