Saved in:
Bibliographic Details
Main Authors: Zhao, Xiaoming, Colburn, Alex, Ma, Fangchang, Bautista, Miguel Angel, Susskind, Joshua M., Schwing, Alexander G.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2310.08587
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910336325517312
author Zhao, Xiaoming
Colburn, Alex
Ma, Fangchang
Bautista, Miguel Angel
Susskind, Joshua M.
Schwing, Alexander G.
author_facet Zhao, Xiaoming
Colburn, Alex
Ma, Fangchang
Bautista, Miguel Angel
Susskind, Joshua M.
Schwing, Alexander G.
contents Rendering scenes observed in a monocular video from novel viewpoints is a challenging problem. For static scenes the community has studied both scene-specific optimization techniques, which optimize on every test scene, and generalized techniques, which only run a deep net forward pass on a test scene. In contrast, for dynamic scenes, scene-specific optimization techniques exist, but, to our best knowledge, there is currently no generalized method for dynamic novel view synthesis from a given monocular video. To answer whether generalized dynamic novel view synthesis from monocular videos is possible today, we establish an analysis framework based on existing techniques and work toward the generalized approach. We find a pseudo-generalized process without scene-specific appearance optimization is possible, but geometrically and temporally consistent depth estimates are needed. Despite no scene-specific appearance optimization, the pseudo-generalized approach improves upon some scene-specific methods.
format Preprint
id arxiv_https___arxiv_org_abs_2310_08587
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Pseudo-Generalized Dynamic View Synthesis from a Video
Zhao, Xiaoming
Colburn, Alex
Ma, Fangchang
Bautista, Miguel Angel
Susskind, Joshua M.
Schwing, Alexander G.
Computer Vision and Pattern Recognition
Rendering scenes observed in a monocular video from novel viewpoints is a challenging problem. For static scenes the community has studied both scene-specific optimization techniques, which optimize on every test scene, and generalized techniques, which only run a deep net forward pass on a test scene. In contrast, for dynamic scenes, scene-specific optimization techniques exist, but, to our best knowledge, there is currently no generalized method for dynamic novel view synthesis from a given monocular video. To answer whether generalized dynamic novel view synthesis from monocular videos is possible today, we establish an analysis framework based on existing techniques and work toward the generalized approach. We find a pseudo-generalized process without scene-specific appearance optimization is possible, but geometrically and temporally consistent depth estimates are needed. Despite no scene-specific appearance optimization, the pseudo-generalized approach improves upon some scene-specific methods.
title Pseudo-Generalized Dynamic View Synthesis from a Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2310.08587