Centre dedocumentation
scientifique

3D hand mesh reconstruction from a monocular RGB image / Hao Peng in The Visual Computer, vol 36 n° 10 - 12 (October 2020)  

Public [article]  inThe Visual Computer > vol 36 n° 10 - 12 (October 2020) . - pp pages2227 - 2239 Titre : 3D hand mesh reconstruction from a monocular RGB image Type de document : Article/Communication Auteurs : Hao Peng, Auteur ; Chuhua Xian, Auteur ; Yunbo Zhang, Auteur Année de publication : 2020 Article en page(s) : pp pages2227 - 2239 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] estimation de pose [Termes descripteurs IGN] image de synthèse [Termes descripteurs IGN] image RVB [Termes descripteurs IGN] maillage [Termes descripteurs IGN] modélisation 3D [Termes descripteurs IGN] réalité augmentée [Termes descripteurs IGN] réalité virtuelle [Termes descripteurs IGN] reconstruction 3D [Termes descripteurs IGN] reconstruction d'objet [Termes descripteurs IGN] vision monoculaire Résumé : (auteur) Most of the existing methods for 3D hand analysis based on RGB images mainly focus on estimating hand keypoints or poses, which cannot capture geometric details of the 3D hand shape. In this work, we propose a novel method to reconstruct a 3D hand mesh from a single monocular RGB image. Different from current parameter-based or pose-based methods, our proposed method directly estimates the 3D hand mesh based on graph convolution neural network (GCN). Our network consists of two modules: the hand localization and mask generation module, and the 3D hand mesh reconstruction module. The first module, which is a VGG16-based network, is applied to localize the hand region in the input image and generate the binary mask of the hand. The second module takes the high-order features from the first and uses a GCN-based network to estimate the coordinates of each vertex of the hand mesh and reconstruct the 3D hand shape. To achieve better accuracy, a novel loss based on the differential properties of the discrete mesh is proposed. We also use professional software to create a large synthetic dataset that contains both ground truth 3D hand meshes and poses for training. To handle the real-world data, we use the CycleGAN network to transform the data domain of real-world images to that of our synthesis dataset. We demonstrate that our method can produce accurate 3D hand mesh and achieve an efficient performance for real-time applications. Numéro de notice : A2020-596 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00371-020-01908-3 date de publication en ligne : 14/07/2020 En ligne : https://doi.org/10.1007/s00371-020-01908-3 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95936 [article]

Guided feature matching for multi-epoch historical image blocks pose estimation / Lulin Zhang in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2 (August 2020)    

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > V-2 (August 2020) . - pp 127 - 134 Titre : Guided feature matching for multi-epoch historical image blocks pose estimation Type de document : Article/Communication Auteurs : Lulin Zhang, Auteur ; Ewelina Rupnik , Auteur ; Marc Pierrot-Deseilligny , Auteur Congrès : Congrès: ISPRS 2020, virtual Congress Imaging today foreseeing tomorrow (31 aout - 2 septembre 2020; Nice, France) , Commanditaire Année de publication : 2020 Projets : DISRUPT / Klinger, Yann Article en page(s) : pp 127 - 134 Note générale : Bibliographie Dans HAL https://hal.archives-ouvertes.fr/hal-02563454 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] appariement d'images [Termes descripteurs IGN] appariement de points [Termes descripteurs IGN] bloc d'images [Termes descripteurs IGN] estimation de pose [Termes descripteurs IGN] image aérienne [Termes descripteurs IGN] mesure de similitude multidimensionnelle [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] Pézenas [Termes descripteurs IGN] point d'appui [Termes descripteurs IGN] point de liaison (imagerie) [Termes descripteurs IGN] SIFT (algorithme) Résumé : (Auteur) Historical aerial imagery plays an important role in providing unique information about evolution of our landscapes. It possesses many positive qualities such as high spatial resolution, stereoscopic configuration and short time interval. Self-calibration reamains a main bottleneck for achieving the intrinsic value of historical imagery, as it involves certain underdeveloped research points such as detecting inter-epoch tie-points. In this research, we present a novel algorithm to detecting inter-epoch tie-points in historical images which do not rely on any auxiliary data. Using SIFT-detected keypoints we perform matching across epochs by interchangeably estimating and imposing that points follow two mathematical models: at first a 2D spatial similarity, then a 3D spatial similarity. We import GCPs to quantitatively evaluate our results with Digital Elevation Models (DEM) of differences (abbreviated as DoD) in absolute reference frame, and compare the results of our method with other 2 methods that use either the traditional SIFT or few virtual GCPs. The experiments show that far more correct inter-epoch tie-points can be extracted with our guided technique. Qualitative and quantitative results are reported. Numéro de notice : A2020-411 Affiliation des auteurs : LaSTIG (2020- ) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-V-2-2020-127-2020 date de publication en ligne : 03/08/2020 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2020-127-2020 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95081 [article]

Documents numériques

en open access Guided feature matching... - pdf auteur Adobe Acrobat PDF

Towards structureless bundle adjustment with two- and three-view structure approximation / Ewelina Rupnik in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2 (August 2020)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > V-2 (August 2020) . - pp 71 - 78 Titre : Towards structureless bundle adjustment with two- and three-view structure approximation Type de document : Article/Communication Auteurs : Ewelina Rupnik , Auteur ; Marc Pierrot-Deseilligny , Auteur Congrès : Congrès: ISPRS 2020, virtual Congress Imaging today foreseeing tomorrow (31 aout - 2 septembre 2020; Nice, France) , Commanditaire Année de publication : 2020 Projets : 1-Pas de projet / Article en page(s) : pp 71 - 78 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes descripteurs IGN] approximation [Termes descripteurs IGN] compensation par faisceaux [Termes descripteurs IGN] estimation de pose [Termes descripteurs IGN] structure-from-motion Résumé : (auteur) The global approaches solve SfM problems by independently inferring relative motions, followed be a sequential estimation of global rotations and translations. It is a fast approach but not optimal because it relies only on pairs and triplets of images and it is not a joint optimisation. In this publication we present a methodology that increases the quality of global solutions without the usual computational burden tied to the bundle adjustment. We propose an efficient structure approximation approach that relies on relative motions known upfront. Using the approximated structure, we are capable of refining the initial poses at very low computational cost. Compared to different benchmark datasets and software solutions, our approach improves the processing times while maintaining good accuracy. Numéro de notice : A2020-505 Affiliation des auteurs : LaSTIG (2020- ) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-V-2-2020-71-2020 date de publication en ligne : 03/08/2020 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2020-71-2020 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95646 [article]

Automatic scale estimation of structure from motion based 3D models using laser scalers in underwater scenarios / Klemen Istenič in ISPRS Journal of photogrammetry and remote sensing, vol 159 (January 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 159 (January 2020) . - pp 13 - 25 Titre : Automatic scale estimation of structure from motion based 3D models using laser scalers in underwater scenarios Type de document : Article/Communication Auteurs : Klemen Istenič, Auteur ; Nuno Gracias, Auteur ; Aurélien Arnaubec, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 13 - 25 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] estimation de pose [Termes descripteurs IGN] étalonnage [Termes descripteurs IGN] faisceau laser [Termes descripteurs IGN] image à haute résolution [Termes descripteurs IGN] image sous-marine [Termes descripteurs IGN] photogrammétrie sous-marine [Termes descripteurs IGN] Ransac (algorithme) [Termes descripteurs IGN] reconstruction 3D [Termes descripteurs IGN] structure-from-motion Résumé : (Auteur) Improvements in structure-from-motion techniques are enabling many scientific fields to benefit from the routine creation of detailed 3D models. However, for a large number of applications, only a single camera is available for the image acquisition, due to cost or space constraints in the survey platforms. Monocular structure-from-motion raises the issue of properly estimating the scale of the 3D models, in order to later use those models for metrology. The scale can be determined from the presence of visible objects of known dimensions, or from information on the magnitude of the camera motion provided by other sensors, such as GPS. This paper addresses the problem of accurately scaling 3D models created from monocular cameras in GPS-denied environments, such as in underwater applications. Motivated by the common availability of underwater laser scalers, we present two novel approaches which are suitable for different laser scaler configurations. A fully unconstrained method enables the use of arbitrary laser setups, while a partially constrained method reduces the need for calibration by only assuming parallelism on the laser beams and equidistance with the camera. The proposed methods have several advantages with respect to existing methods. By using the known geometry of the scene represented by the 3D model, along with some parameters of the laser scaler geometry, the need for laser alignment with the optical axis of the camera is eliminated. Furthermore, the extremely error-prone manual identification of image points on the 3D model, currently required in image-scaling methods, is dispensed with. The performance of the methods and their applicability was evaluated both on data generated from a realistic 3D model and on data collected during an oceanographic cruise in 2017. Three separate laser configurations have been tested, encompassing nearly all possible laser setups, to evaluate the effects of terrain roughness, noise, camera perspective angle and camera-scene distance on the final estimates of scale. In the real scenario, the computation of 6 independent model scale estimates using our fully unconstrained approach, produced values with a standard deviation of 0,3 %. By comparing the values to the only other possible method currently usable for this dataset, we showed that the consistency of scales obtained for individual lasers is much higher for our approach (0,6 % compared to 4 %). Numéro de notice : A2020-010 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.10.007 date de publication en ligne : 14/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.10.007 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94397 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020011	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020013	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2020012	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Robust pose estimation and calibration of catadioptric cameras with spherical mirrors / Sagi Filin in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 1 (January 2020)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 86 n° 1 (January 2020) . - pp 33 - 44 Titre : Robust pose estimation and calibration of catadioptric cameras with spherical mirrors Type de document : Article/Communication Auteurs : Sagi Filin, Auteur ; Grigory Ilizirov, Auteur ; Bashar Elnashef, Auteur Année de publication : 2020 Article en page(s) : pp 33 - 44 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s) [Termes descripteurs IGN] estimation de pose [Termes descripteurs IGN] étalonnage de chambre métrique [Termes descripteurs IGN] flux lumineux [Termes descripteurs IGN] lentille [Termes descripteurs IGN] méthode robuste [Termes descripteurs IGN] miroir [Termes descripteurs IGN] reconstruction 3D [Termes descripteurs IGN] sphère [Termes descripteurs IGN] trilatération Résumé : (Auteur) Catadioptric cameras broaden the field of view and reveal otherwise occluded object parts. They differ geometrically from central-perspective cameras because of light reflection from the mirror surface. To handle these effects, we present new pose-estimation and reconstruction models for imaging through spherical mirrors. We derive a closed-form equivalent to the collinearity principle via which three methods are established to estimate the system parameters: a resection-based one, a trilateration-based one that introduces novel constraints that enhance accuracy, and a direct and linear transform-based one. The estimated system parameters exhibit improved accuracy compared to the state of the art, and analysis shows intrinsic robustness to the presence of a high fraction of outliers. We then show that 3D point reconstruction can be performed at accurate levels. Thus, we provide an in-depth look into the geometrical modeling of spherical catadioptric systems and practical enhancements of accuracies and requirements to reach them. Numéro de notice : A2020-050 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.86.1.33 date de publication en ligne : 01/01/2020 En ligne : https://doi.org/10.14358/PERS.86.1.33 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94535 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2020011	SL	Revue	Centre de documentation	Revues en salle	Disponible

Simulation and analysis of photogrammetric UAV image blocks: influence of camera calibration error / Yilin Zhou in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, IV-2/W5 (May 2019)  

Permalink

BIM-PoseNet: Indoor camera localisation using a 3D indoor model and deep learning from synthetic images / Debaditya Acharya in ISPRS Journal of photogrammetry and remote sensing, vol 150 (April 2019)  

Permalink

BIM-Tracker: A model-based visual tracking approach for indoor localisation using a 3D building model / Debaditya Acharya in ISPRS Journal of photogrammetry and remote sensing, vol 150 (April 2019)  

Permalink

Equivalent constraints for two-view geometry : Pose solution/pure rotation identification and 3D reconstruction / Qi Cai in International journal of computer vision, vol 127 n° 2 (February 2019)  

Permalink

Geometric camera pose refinement with learned depth maps / Nathan Piasco (2019)  

Permalink

Perspective-n-learned-point: pose estimation from relative depth / Nathan Piasco (2019)    

Permalink

Structure from motion for ordered and unordered image sets based on random k-d forests and global pose estimation / Xin Wang in ISPRS Journal of photogrammetry and remote sensing, vol 147 (January 2019)  

Permalink

Depth-based hand pose estimation : Methods, data, and challenges / James Steven Supančič in International journal of computer vision, vol 126 n° 11 (November 2018)  

Permalink

3D urban geovisualization: in situ augmented and mixed reality experiments / Alexandre Devaux in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, IV-4 ([19/09/2018])    

Permalink

Image-based synthesis for deep 3D human pose estimation / Grégory Rogez in International journal of computer vision, vol 126 n° 9 (September 2018)  

Permalink