EUVIMEDEUVIMED entdecken
Crossref

Neural 3D Scene Reconstruction With Indoor Planar Priors

Xiaowei Zhou, Haoyu Guo, Sida Peng, Yuxi Xiao, Haotong Lin, Qianqian Wang, Guofeng Zhang, Hujun Bao

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-09 · 46 (9) · 6355-6366

DOI: 10.1109/tpami.2024.3379833 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-09. Verfasst von Xiaowei Zhou und 7 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 78 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Information Technology Center, Nagoya University, State Key Lab of CAD&CG.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper addresses the challenge of reconstructing 3D indoor scenes from multi-view images. Many previous works have shown impressive reconstruction results on textured objects, but they still have difficulty in handling low-textured planar regions, which are common in indoor scenes. An approach to solving this issue is to incorporate planar constraints into the depth map estimation in multi-view stereo-based methods, but the per-view plane estimation and depth optimization lack both efficiency and multi-view consistency. In this work, we show that the planar constraints can be conveniently integrated into the recent implicit neural representation-based reconstruction methods. Specifically, we use an MLP network to represent the signed distance function as the scene geometry. Based on the Manhattan-world assumption and the Atlanta-world assumption, planar constraints are employed to regularize the geometry in floor and wall regions predicted by a 2D semantic segmentation network. To resolve the inaccurate segmentation, we encode the semantics of 3D points with another MLP and design a novel loss that jointly optimizes the scene geometry and semantics in 3D space. Experiments on ScanNet and 7-Scenes datasets show that the proposed method outperforms previous methods by a large margin on 3D reconstruction quality.

Förderung

  • National Key Research and Development Program of China
  • Information Technology Center, Nagoya University
  • State Key Lab of CAD&CG
  • Zhejiang University

Zitieren

APA

Zhou, X., Guo, H., Peng, S., Xiao, Y., Lin, H., Wang, Q., Zhang, G., & Bao, H. (2024). Neural 3D Scene Reconstruction With Indoor Planar Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(9), 6355-6366. https://doi.org/10.1109/tpami.2024.3379833

Vancouver

Zhou X, Guo H, Peng S, Xiao Y, Lin H, Wang Q, et al. Neural 3D Scene Reconstruction With Indoor Planar Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(9):6355-6366. doi:10.1109/tpami.2024.3379833

BibTeX
@article{Zhou2024,
  author = {Zhou, Xiaowei and Guo, Haoyu and Peng, Sida and Xiao, Yuxi and Lin, Haotong and Wang, Qianqian and Zhang, Guofeng and Bao, Hujun},
  title = {Neural 3D Scene Reconstruction With Indoor Planar Priors},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {9},
  pages = {6355--6366},
  doi = {10.1109/tpami.2024.3379833}
}
Kostenlos starten →