Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations

Author:

Sajjadi Mehdi S.M.1,Meyer Henning1,Pot Etienne1,Bergmann Urs1,Greff Klaus1,Radwan Noha1,Vora Suhani1,Lucic Mario1,Duckworth Daniel1,Dosovitskiy Alexey1,Uszkoreit Jakob1,Funkhouser Thomas1,Tagliasacchi Andrea2

Affiliation:

1. Google Research

2. Simon Fraser University

Publisher

IEEE

Reference52 articles.

1. State of the Art on Neural Rendering

2. Light field networks: Neural scene representations with single-evaluation rendering;sitzmann;NeurIPS,2021

3. EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis

4. Geometryfree view synthesis: Transformers and no 3D priors;rombach;ICCV,2021

5. Mesh-based 3D textured urban mapping

Cited by 27 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Car-Studio: Learning Car Radiance Fields From Single-View and Unlimited In-the-Wild Images;IEEE Robotics and Automation Letters;2024-03

2. 360° Reconstruction From a Single Image Using Space Carved Outpainting;SIGGRAPH Asia 2023 Conference Papers;2023-12-10

3. iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis;SIGGRAPH Asia 2023 Conference Papers;2023-12-10

4. A Survey on Deep Generative 3D-aware Image Synthesis;ACM Computing Surveys;2023-11-09

5. Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3