Gen3DSR: Generalizable 3D Scene Reconstruction Via Divide and Conquer From a Single View

Ardelean A, Özer M, Egger B (2025)

Publication Language: English

Publication Type: Conference contribution

Publication year: 2025

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 616-626

Conference Proceedings Title: 2025 International Conference on 3D Vision (3DV)

Event location: Singapore SG

ISBN: 979-8-3315-3852-1

DOI: 10.1109/3DV66043.2025.00062

Abstract

Single-view 3D reconstruction is currently approached from two dominant perspectives: reconstruction of scenes with limited diversity using 3D data supervision or reconstruction of diverse singular objects using large image priors. However, real-world scenarios are far more complex and exceed the capabilities of these methods. We therefore propose a hybrid method following a divide-and-conquer strategy. We first process the scene holistically, extracting depth and semantic information, and then leverage an object-level method for the detailed reconstruction of individual components. By splitting the problem into simpler tasks, our system is able to generalize to various types of scenes without retraining or fine-tuning. We purposely design our pipeline to be highly modular with independent, self-contained modules, to avoid the need for end-to-end training of the whole system. This enables the pipeline to naturally improve as future methods can replace the individual modules. We demonstrate the reconstruction performance of our approach on both synthetic and real-world scenes, comparing favorable against prior works. Project page: https://andreeadogaru.github.io/Gen3DSR

Authors with CRIS profile

Andreea Ardelean Juniorprofessur für Cognitive Computer Vision (Stiftungsprofessur) Mert Özer Juniorprofessur für Cognitive Computer Vision (Stiftungsprofessur) Bernhard Egger Juniorprofessur für Cognitive Computer Vision (Stiftungsprofessur)

How to cite

APA:

Ardelean, A., Özer, M., & Egger, B. (2025). Gen3DSR: Generalizable 3D Scene Reconstruction Via Divide and Conquer From a Single View. In 2025 International Conference on 3D Vision (3DV) (pp. 616-626). Singapore, SG: Institute of Electrical and Electronics Engineers Inc..

MLA:

Ardelean, Andreea, Mert Özer, and Bernhard Egger. "Gen3DSR: Generalizable 3D Scene Reconstruction Via Divide and Conquer From a Single View." Proceedings of the 12th International Conference on 3D Vision, 3DV 2025, Singapore Institute of Electrical and Electronics Engineers Inc., 2025. 616-626.

BibTeX: Download