Centre de documentation
scientifique

GeoRec: Geometry-enhanced semantic 3D reconstruction of RGB-D indoor scenes / Linxi Huan in ISPRS Journal of photogrammetry and remote sensing, vol 186 (April 2022)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 186 (April 2022) . - pp 301 - 314 Titre : GeoRec: Geometry-enhanced semantic 3D reconstruction of RGB-D indoor scenes Type de document : Article/Communication Auteurs : Linxi Huan, Auteur ; Xianwei Zheng, Auteur ; Jianya Gong, Auteur Année de publication : 2022 Article en page(s) : pp 301 - 314 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] données localisées 3D [Termes IGN] géométrie [Termes IGN] image RVB [Termes IGN] maillage [Termes IGN] modélisation sémantique [Termes IGN] objet 3D [Termes IGN] reconstruction 3D [Termes IGN] reconstruction d'objet [Termes IGN] scène intérieure Résumé : (auteur) Semantic indoor 3D modeling with multi-task deep neural networks is an efficient and low-cost way for reconstructing an indoor scene with geometrically complete room structure and semantic 3D individuals. Challenged by the complexity and clutter of indoor scenarios, the semantic reconstruction quality of current methods is still limited by the insufficient exploration and learning of 3D geometry information. To this end, this paper proposes an end-to-end multi-task neural network for geometry-enhanced semantic 3D reconstruction of RGB-D indoor scenes (termed as GeoRec). In the proposed GeoRec, we build a geometry extractor that can effectively learn geometry-enhanced feature representation from depth data, to improve the estimation accuracy of layout, camera pose and 3D object bounding boxes. We also introduce a novel object mesh generator that strengthens the reconstruction robustness of GeoRec to indoor occlusion with geometry-enhanced implicit shape embedding. With the parsed scene semantics and geometries, the proposed GeoRec reconstructs an indoor scene by placing reconstructed object mesh models with 3D object detection results in the estimated layout cuboid. Extensive experiments conducted on two benchmark datasets show that the proposed GeoRec yields outstanding performance with mean chamfer distance error for object reconstruction on the challenging Pix3D dataset, 70.45% mAP for 3D object detection and 77.1% 3D mIoU for layout estimation on the commonly-used SUN RGB-D dataset. Especially, the mesh reconstruction sub-network of GeoRec trained on Pix3D can be directly transferred to SUN RGB-D without any fine-tuning, manifesting a high generalization ability. Numéro de notice : A2022-235 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2022.02.014 Date de publication en ligne : 03/03/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.02.014 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100139 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2022041	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2022043	DEP-RECP	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2022042	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Parsing very high resolution urban scene images by learning deep ConvNets with edge-aware loss / Xianwei Zheng in ISPRS Journal of photogrammetry and remote sensing, vol 170 (December 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 170 (December 2020) . - pp 15-28 Titre : Parsing very high resolution urban scene images by learning deep ConvNets with edge-aware loss Type de document : Article/Communication Auteurs : Xianwei Zheng, Auteur ; Linxi Huan, Auteur ; Gui-Song Xia, Auteur ; Jianya Gong, Auteur Année de publication : 2020 Article en page(s) : pp 15-28 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification basée sur les régions [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] contour [Termes IGN] image à très haute résolution [Termes IGN] méthode fondée sur le noyau [Termes IGN] scène urbaine [Termes IGN] segmentation sémantique Résumé : (Auteur) Parsing very high resolution (VHR) urban scene images into regions with semantic meaning, e.g. buildings and cars, is a fundamental task in urban scene understanding. However, due to the huge quantity of details contained in an image and the large variations of objects in scale and appearance, the existing semantic segmentation methods often break one object into pieces, or confuse adjacent objects and thus fail to depict these objects consistently. To address these issues uniformly, we propose a standalone end-to-end edge-aware neural network (EaNet) for urban scene semantic segmentation. For semantic consistency preservation inside objects, the EaNet model incorporates a large kernel pyramid pooling (LKPP) module to capture rich multi-scale context with strong continuous feature relations. To effectively separate confusing objects with sharp contours, a Dice-based edge-aware loss function (EA loss) is devised to guide the EaNet to refine both the pixel- and image-level edge information directly from semantic segmentation prediction. In the proposed EaNet model, the LKPP and the EA loss couple to enable comprehensive feature learning across an entire semantic object. Extensive experiments on three challenging datasets demonstrate that our method can be readily generalized to multi-scale ground/aerial urban scene images, achieving 81.7% in mIoU on Cityscapes Test set and 90.8% in the mean F1-score on the ISPRS Vaihingen 2D Test set. Code is available at: https://github.com/geovsion/EaNet. Numéro de notice : A2020-703 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.09.019 Date de publication en ligne : 14/10/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.09.019 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96228 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020121	RAB	Revue	Centre de documentation	En réserve L003	Disponible

A morphologically preserved multi-resolution TIN surface modeling and visualization method for virtual globes / Xianwei Zheng in ISPRS Journal of photogrammetry and remote sensing, vol 129 (July 2017)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 129 (July 2017) . - pp 41 - 54 Titre : A morphologically preserved multi-resolution TIN surface modeling and visualization method for virtual globes Type de document : Article/Communication Auteurs : Xianwei Zheng, Auteur ; Hanjiang Xiong, Auteur ; Jianya Gong, Auteur ; Linwei Yue, Auteur Année de publication : 2017 Article en page(s) : pp 41 - 54 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] analyse multiéchelle [Termes IGN] arbre quadratique [Termes IGN] globe virtuel [Termes IGN] représentation cartographique 3D [Termes IGN] représentation du relief [Termes IGN] tessellation [Termes IGN] Triangulated Irregular Network Résumé : (Auteur) Virtual globes play an important role in representing three-dimensional models of the Earth. To extend the functioning of a virtual globe beyond that of a “geobrowser”, the accuracy of the geospatial data in the processing and representation should be of special concern for the scientific analysis and evaluation. In this study, we propose a method for the processing of large-scale terrain data for virtual globe visualization and analysis. The proposed method aims to construct a morphologically preserved multi-resolution triangulated irregular network (TIN) pyramid for virtual globes to accurately represent the landscape surface and simultaneously satisfy the demands of applications at different scales. By introducing cartographic principles, the TIN model in each layer is controlled with a data quality standard to formulize its level of detail generation. A point-additive algorithm is used to iteratively construct the multi-resolution TIN pyramid. The extracted landscape features are also incorporated to constrain the TIN structure, thus preserving the basic morphological shapes of the terrain surface at different levels. During the iterative construction process, the TIN in each layer is seamlessly partitioned based on a virtual node structure, and tiled with a global quadtree structure. Finally, an adaptive tessellation approach is adopted to eliminate terrain cracks in the real-time out-of-core spherical terrain rendering. The experiments undertaken in this study confirmed that the proposed method performs well in multi-resolution terrain representation, and produces high-quality underlying data that satisfy the demands of scientific analysis and evaluation. Numéro de notice : A2017-346 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2017.04.013 En ligne : https://dx.doi.org/10.1016/j.isprsjprs.2017.04.013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85606 [article]

Exemplaires(3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2017071	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2017073	DEP-EXM	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2017072	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

An improved ANUDEM method combining topographic correction and DEM interpolation / Xianwei Zheng in Geocarto international, vol 31 n° 5 - 6 (May - June 2016)  

Public [article]  inGeocarto international > vol 31 n° 5 - 6 (May - June 2016) . - pp 492 - 505 Titre : An improved ANUDEM method combining topographic correction and DEM interpolation Type de document : Article/Communication Auteurs : Xianwei Zheng, Auteur ; H. Xiong, Auteur ; Jianya Gong, Auteur ; Linwei Yue, Auteur Année de publication : 2016 Article en page(s) : pp 492 - 505 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] contour [Termes IGN] correction topographique [Termes IGN] détail topographique [Termes IGN] interpolation spatiale [Termes IGN] modèle numérique de surface [Termes IGN] relief Résumé : (Auteur) Void filling and anomaly replacement in conjunction with auxiliary sources of data have been widely used to improve the quality of existing problematic high-resolution digital elevation models. However, the traditional interpolation methods used for this purpose have always failed to eliminate the discrepancies between different data-sets. In this paper, an improved ANUDEM method is presented for DEM interpolation, which incorporates the idea of topographic correction using high correlation of topological structure between contour lines (CLs) from multi-scale digital elevation models (DEM). Firstly, the terrain topological structure is extracted from the CLs of a low-resolution DEM. The topographic surface correction is then undertaken based on the extracted structure, which recovers the topographic information of the sharp depressions and eminences to fit the high-resolution representation. Finally, the breaklines of the terrain surface are distilled and integrated into the denser DEM generation. The experiments undertaken confirmed the superiority of the proposed method over the other DEM interpolation methods. It is shown that the proposed method can provide results with a higher accuracy, as well as a better visual quality. Numéro de notice : A2016-168 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2015.1059899 Date de publication en ligne : 11/07/2015 En ligne : http://www.tandfonline.com/doi/full/10.1080/10106049.2015.1059899 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80507 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2016031	RAB	Revue	Centre de documentation	En réserve L003	Disponible