Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tang, Zhenggang, Ren, Zhongzheng, Zhao, Xiaoming, Wen, Bowen, Tremblay, Jonathan, Birchfield, Stan, Schwing, Alexander
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2406.10543
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914835133890560
author Tang, Zhenggang
Ren, Zhongzheng
Zhao, Xiaoming
Wen, Bowen
Tremblay, Jonathan
Birchfield, Stan
Schwing, Alexander
author_facet Tang, Zhenggang
Ren, Zhongzheng
Zhao, Xiaoming
Wen, Bowen
Tremblay, Jonathan
Birchfield, Stan
Schwing, Alexander
contents We present a method for automatically modifying a NeRF representation based on a single observation of a non-rigid transformed version of the original scene. Our method defines the transformation as a 3D flow, specifically as a weighted linear blending of rigid transformations of 3D anchor points that are defined on the surface of the scene. In order to identify anchor points, we introduce a novel correspondence algorithm that first matches RGB-based pairs, then leverages multi-view information and 3D reprojection to robustly filter false positives in two steps. We also introduce a new dataset for exploring the problem of modifying a NeRF scene through a single observation. Our dataset ( https://github.com/nerfdeformer/nerfdeformer ) contains 113 synthetic scenes leveraging 47 3D assets. We show that our proposed method outperforms NeRF editing methods as well as diffusion-based methods, and we also explore different methods for filtering correspondences.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10543
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows
Tang, Zhenggang
Ren, Zhongzheng
Zhao, Xiaoming
Wen, Bowen
Tremblay, Jonathan
Birchfield, Stan
Schwing, Alexander
Computer Vision and Pattern Recognition
Artificial Intelligence
We present a method for automatically modifying a NeRF representation based on a single observation of a non-rigid transformed version of the original scene. Our method defines the transformation as a 3D flow, specifically as a weighted linear blending of rigid transformations of 3D anchor points that are defined on the surface of the scene. In order to identify anchor points, we introduce a novel correspondence algorithm that first matches RGB-based pairs, then leverages multi-view information and 3D reprojection to robustly filter false positives in two steps. We also introduce a new dataset for exploring the problem of modifying a NeRF scene through a single observation. Our dataset ( https://github.com/nerfdeformer/nerfdeformer ) contains 113 synthetic scenes leveraging 47 3D assets. We show that our proposed method outperforms NeRF editing methods as well as diffusion-based methods, and we also explore different methods for filtering correspondences.
title NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.10543