Descripteur
Documents disponibles dans cette catégorie (12)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externesEtendre la recherche sur niveau(x) vers le bas
Semantic hierarchy emerges in deep generative representations for scene synthesis / Ceyuan Yang in International journal of computer vision, vol 129 n° 5 (May 2021)
Titre : Semantic hierarchy emerges in deep generative representations for scene synthesis Type de document : Article/Communication Auteurs : Ceyuan Yang, Auteur ; Yujun Shen, Auteur ; Bolei Zhou, Auteur Année de publication : 2021 Article en page(s) : pp 1451 - 1466 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse visuelle
[Termes IGN] apprentissage profond
[Termes IGN] compréhension de l'image
[Termes IGN] représentation des connaissances
[Termes IGN] réseau antagoniste génératif
[Termes IGN] segmentation hiérarchique
[Termes IGN] segmentation sémantique
[Termes IGN] synthèse d'imageRésumé : (auteur) Despite the great success of Generative Adversarial Networks (GANs) in synthesizing images, there lacks enough understanding of how photo-realistic images are generated from the layer-wise stochastic latent codes introduced in recent GANs. In this work, we show that highly-structured semantic hierarchy emerges in the deep generative representations from the state-of-the-art GANs like StyleGAN and BigGAN, trained for scene synthesis. By probing the per-layer representation with a broad set of semantics at different abstraction levels, we manage to quantify the causality between the layer-wise activations and the semantics occurring in the output image. Such a quantification identifies the human-understandable variation factors that can be further used to steer the generation process, such as changing the lighting condition and varying the viewpoint of the scene. Extensive qualitative and quantitative results suggest that the generative representations learned by the GANs with layer-wise latent codes are specialized to synthesize various concepts in a hierarchical manner: the early layers tend to determine the spatial layout, the middle layers control the categorical objects, and the later layers render the scene attributes as well as the color scheme. Identifying such a set of steerable variation factors facilitates high-fidelity scene editing based on well-learned GAN models without any retraining (code and demo video are available at https://genforce.github.io/higan). Numéro de notice : A2021-408 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s11263-020-01429-5 Date de publication en ligne : 10/02/2021 En ligne : https://doi.org/10.1007/s11263-020-01429-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97725
in International journal of computer vision > vol 129 n° 5 (May 2021) . - pp 1451 - 1466[article]
Titre : A shape transformation-based dataset augmentation framework for pedestrian detection Type de document : Article/Communication Auteurs : Zhe Chen, Auteur ; Wanli Ouyang, Auteur ; Tongliang Liu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1121 - 1138 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage par transformation
[Termes IGN] apprentissage profond
[Termes IGN] déformation d'objet
[Termes IGN] détection de piéton
[Termes IGN] jeu de données
[Termes IGN] synthèse d'image
[Termes IGN] vision par ordinateurRésumé : (auteur) Deep learning-based computer vision is usually data-hungry. Many researchers attempt to augment datasets with synthesized data to improve model robustness. However, the augmentation of popular pedestrian datasets, such as Caltech and Citypersons, can be extremely challenging because real pedestrians are commonly in low quality. Due to the factors like occlusions, blurs, and low-resolution, it is significantly difficult for existing augmentation approaches, which generally synthesize data using 3D engines or generative adversarial networks (GANs), to generate realistic-looking pedestrians. Alternatively, to access much more natural-looking pedestrians, we propose to augment pedestrian detection datasets by transforming real pedestrians from the same dataset into different shapes. Accordingly, we propose the Shape Transformation-based Dataset Augmentation (STDA) framework. The proposed framework is composed of two subsequent modules, i.e. the shape-guided deformation and the environment adaptation. In the first module, we introduce a shape-guided warping field to help deform the shape of a real pedestrian into a different shape. Then, in the second stage, we propose an environment-aware blending map to better adapt the deformed pedestrians into surrounding environments, obtaining more realistic-llooking pedestrians and more beneficial augmentation results for pedestrian detection. Extensive empirical studies on different pedestrian detection benchmarks show that the proposed STDA framework consistently produces much better augmentation results than other pedestrian synthesis approaches using low-quality pedestrians. By augmenting the original datasets, our proposed framework also improves the baseline pedestrian detector by up to 38% on the evaluated benchmarks, achieving state-of-the-art performance. Numéro de notice : A2021-354 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s11263-020-01412-0 Date de publication en ligne : 09/01/2021 En ligne : https://doi.org/10.1007/s11263-020-01412-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97606
in International journal of computer vision > vol 129 n° 4 (April 2021) . - pp 1121 - 1138[article]
Titre : Configurable 3D scene synthesis and 2D image rendering with per-pixel ground truth using stochastic grammars Type de document : Article/Communication Auteurs : Chenfanfu Jiang, Auteur ; Shuyao Qi, Auteur ; Yixin Zhu, Auteur ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 920 - 941 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage automatique
[Termes IGN] architecture pipeline (processeur)
[Termes IGN] compréhension de l'image
[Termes IGN] image RVB
[Termes IGN] rendu réaliste
[Termes IGN] scène intérieure
[Termes IGN] segmentation sémantique
[Termes IGN] synthèse d'imageRésumé : (Auteur) We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of training, benchmarking, and diagnosing learning-based computer vision and robotics algorithms. In particular, we devise a learning-based pipeline of algorithms capable of automatically generating and rendering a potentially infinite variety of indoor scenes by using a stochastic grammar, represented as an attributed Spatial And-Or Graph, in conjunction with state-of-the-art physics-based rendering. Our pipeline is capable of synthesizing scene layouts with high diversity, and it is configurable inasmuch as it enables the precise customization and control of important attributes of the generated scenes. It renders photorealistic RGB images of the generated scenes while automatically synthesizing detailed, per-pixel ground truth data, including visible surface depth and normal, object identity, and material information (detailed to object parts), as well as environments (e.g., illuminations and camera viewpoints). We demonstrate the value of our synthesized dataset, by improving performance in certain machine-learning-based scene understanding tasks—depth and surface normal prediction, semantic segmentation, reconstruction, etc.—and by providing benchmarks for and diagnostics of trained models by modifying object attributes and scene properties in a controllable manner. Numéro de notice : A2018-416 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1103-5 Date de publication en ligne : 30/06/2018 En ligne : https://doi.org/10.1007/s11263-018-1103-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90899
in International journal of computer vision > vol 126 n° 9 (September 2018) . - pp 920 - 941[article]
Titre : Image-based synthesis for deep 3D human pose estimation Type de document : Article/Communication Auteurs : Grégory Rogez, Auteur ; Cordelia Schmid, Auteur Année de publication : 2018 Article en page(s) : pp 993 - 1008 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] apprentissage automatique
[Termes IGN] données localisées 3D
[Termes IGN] estimation de pose
[Termes IGN] réseau neuronal convolutif
[Termes IGN] synthèse d'imageRésumé : (Auteur) This paper addresses the problem of 3D human pose estimation in the wild. A significant challenge is the lack of training data, i.e., 2D images of humans annotated with 3D poses. Such data is necessary to train state-of-the-art CNN architectures. Here, we propose a solution to generate a large set of photorealistic synthetic images of humans with 3D pose annotations. We introduce an image-based synthesis engine that artificially augments a dataset of real images with 2D human pose annotations using 3D motion capture data. Given a candidate 3D pose, our algorithm selects for each joint an image whose 2D pose locally matches the projected 3D pose. The selected images are then combined to generate a new synthetic image by stitching local image patches in a kinematically constrained manner. The resulting images are used to train an end-to-end CNN for full-body 3D pose estimation. We cluster the training data into a large number of pose classes and tackle pose estimation as a K-way classification problem. Such an approach is viable only with large training sets such as ours. Our method outperforms most of the published works in terms of 3D pose estimation in controlled environments (Human3.6M) and shows promising results for real-world images (LSP). This demonstrates that CNNs trained on artificial images generalize well to real images. Compared to data generated from more classical rendering engines, our synthetic images do not require any domain adaptation or fine-tuning stage. Numéro de notice : A2018-418 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-018-1071-9 Date de publication en ligne : 19/03/2018 En ligne : https://doi.org/10.1007/s11263-018-1071-9 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90901
in International journal of computer vision > vol 126 n° 9 (September 2018) . - pp 993 - 1008[article]
Titre : Challenges in adapting example-based texture synthesis for panoramic map creation: a case study Type de document : Article/Communication Auteurs : Helen Jenny, Auteur ; Bernhard Jenny, Auteur Année de publication : 2013 Article en page(s) : pp 297 - 304 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie
[Termes IGN] déformation géométrique
[Termes IGN] image panoramique
[Termes IGN] peinture
[Termes IGN] synthèse d'image
[Termes IGN] texture d'imageRésumé : (Auteur) Panoramic hiking and skiing maps are popular among tourists and map collectors. Such three-dimensional (3D) maps allow for easy orientation and provide the observer with an immersive impression of the landscape to be discovered or remembered. The most impressive panoramic masterpieces are almost exclusively painted manually or with minor digital tool support. Software packages that allow modern cartographers to create 3D maps of comparable visual quality (semi-) automatically are currently not available. Computer graphics has developed a number of methods for painterly rendering, including imitating the characteristics of a panorama artist's brush stroke and raster-based methods that synthesize new texture from examples. In this article, the latter approach is explored, and the idea of creating terrain textures for arbitrary regions by reassembling them from pieces of scanned hand-painted masterworks is pursued. Panorama painters vary the appearance of land cover depending on terrain characteristics and viewing parameters. This article suggests how the example-based texture synthesis approach could be adapted to accommodate such dependencies. A case study of transferring the appearance of H.C. Berann's hand-painted panorama of the Swiss Jungfrau region to a digital panorama of a different region is presented. The case study shows that a number of previously unanticipated hurdles are encountered when using hand-painted panoramas as input to an example-based texture synthesis algorithm. By identifying the challenges of applying texture-by-example to panoramic map making and by suggesting possible solutions, the authors aim to promote the creation of more visually appealing and legible digital panoramic maps. Numéro de notice : A2013-761 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/15230406.2013.795001 En ligne : https://doi.org/10.1080/15230406.2013.795001 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32897
in Cartography and Geographic Information Science > vol 40 n° 4 (September 2013) . - pp 297 - 304[article]Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 032-2013041 RAB Revue Centre de documentation En réserve L003 Disponible PermalinkMathématiques pour la modélisation géométrique, la représentation 3D et la synthèse d'images / L. Garnier (2007)
PermalinkUtilisation de simulations d'images hyperspectrales à partir de base de données 3D pour la spécification de futurs capteurs spatiaux / Audrey Malherbe (2004)
PermalinkPermalinkPermalinkPermalinkPermalink
