loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Maximilian Denninger 1 ; 2 and Rudolph Triebel 1 ; 2

Affiliations: 1 German Aerospace Center (DLR), 82234 Wessling, Germany ; 2 Technical University of Munich (TUM), 80333 Munich, Germany

Keyword(s): 3D Reconstruction, 3D Segmentation, Single View, Sim2real.

Abstract: We introduce a novel method for semantic volumetric reconstructions from a single RGB image. To overcome the problem of semantically reconstructing regions in 3D that are occluded in the 2D image, we propose to combine both in an implicit encoding. By relying on a headless autoencoder, we are able to encode semantic categories and implicit TSDF values into a compressed latent representation. A second network then uses these as a reconstruction target and learns to convert color images into these latent representations, which get decoded after inference. Additionally, we introduce a novel loss-shaping technique for this implicit representation. In our experiments on the realistic benchmark Replica dataset, we achieve a full reconstruction of a scene, which is visually and in terms of quantitative measures better than current methods while only using synthetic data during training. On top of that, we evaluate our approach on color images recorded in the wild.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 216.73.216.157

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Denninger, M., Triebel and R. (2023). 3D Semantic Scene Reconstruction from a Single Viewport. In Proceedings of the 3rd International Conference on Image Processing and Vision Engineering - IMPROVE; ISBN 978-989-758-642-2; ISSN 2795-4943, SciTePress, pages 15-26. DOI: 10.5220/0011747700003497

@conference{improve23,
author={Maximilian Denninger and Rudolph Triebel},
title={3D Semantic Scene Reconstruction from a Single Viewport},
booktitle={Proceedings of the 3rd International Conference on Image Processing and Vision Engineering - IMPROVE},
year={2023},
pages={15-26},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011747700003497},
isbn={978-989-758-642-2},
issn={2795-4943},
}

TY - CONF

JO - Proceedings of the 3rd International Conference on Image Processing and Vision Engineering - IMPROVE
TI - 3D Semantic Scene Reconstruction from a Single Viewport
SN - 978-989-758-642-2
IS - 2795-4943
AU - Denninger, M.
AU - Triebel, R.
PY - 2023
SP - 15
EP - 26
DO - 10.5220/0011747700003497
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic