ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sargent, Kyle, Li, Zizhang, Shah, Tanmay, Herrmann, Charles, Yu, Hong-Xing, Zhang, Yunzhi, Chan, Eric Ryan, Lagun, Dmitry, Fei-Fei, Li, Sun, Deqing, Wu, Jiajun
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913326848540672
author Sargent, Kyle
Li, Zizhang
Shah, Tanmay
Herrmann, Charles
Yu, Hong-Xing
Zhang, Yunzhi
Chan, Eric Ryan
Lagun, Dmitry
Fei-Fei, Li
Sun, Deqing
Wu, Jiajun
author_facet Sargent, Kyle
Li, Zizhang
Shah, Tanmay
Herrmann, Charles
Yu, Hong-Xing
Zhang, Yunzhi
Chan, Eric Ryan
Lagun, Dmitry
Fei-Fei, Li
Sun, Deqing
Wu, Jiajun
contents We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced by in-the-wild multi-object scenes with complex backgrounds. Specifically, we train a generative prior on a mixture of data sources that capture object-centric, indoor, and outdoor scenes. To address issues from data mixture such as depth-scale ambiguity, we propose a novel camera conditioning parameterization and normalization scheme. Further, we observe that Score Distillation Sampling (SDS) tends to truncate the distribution of complex backgrounds during distillation of 360-degree scenes, and propose "SDS anchoring" to improve the diversity of synthesized novel views. Our model sets a new state-of-the-art result in LPIPS on the DTU dataset in the zero-shot setting, even outperforming methods specifically trained on DTU. We further adapt the challenging Mip-NeRF 360 dataset as a new benchmark for single-image novel view synthesis, and demonstrate strong performance in this setting. Our code and data are at http://kylesargent.github.io/zeronvs/
format Preprint
id arxiv_https___arxiv_org_abs_2310_17994
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
Sargent, Kyle
Li, Zizhang
Shah, Tanmay
Herrmann, Charles
Yu, Hong-Xing
Zhang, Yunzhi
Chan, Eric Ryan
Lagun, Dmitry
Fei-Fei, Li
Sun, Deqing
Wu, Jiajun
Computer Vision and Pattern Recognition
Graphics
We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced by in-the-wild multi-object scenes with complex backgrounds. Specifically, we train a generative prior on a mixture of data sources that capture object-centric, indoor, and outdoor scenes. To address issues from data mixture such as depth-scale ambiguity, we propose a novel camera conditioning parameterization and normalization scheme. Further, we observe that Score Distillation Sampling (SDS) tends to truncate the distribution of complex backgrounds during distillation of 360-degree scenes, and propose "SDS anchoring" to improve the diversity of synthesized novel views. Our model sets a new state-of-the-art result in LPIPS on the DTU dataset in the zero-shot setting, even outperforming methods specifically trained on DTU. We further adapt the challenging Mip-NeRF 360 dataset as a new benchmark for single-image novel view synthesis, and demonstrate strong performance in this setting. Our code and data are at http://kylesargent.github.io/zeronvs/
title ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2310.17994