Search

Your search keyword '"Russell, Bryan C."' showing total 37 results
Start Over Author "Russell, Bryan C."
37 results on '"Russell, Bryan C."'

1. Learning elementary structures for 3D shape generation and matching

Author

Deprelle, Theo, Groueix, Thibault, Fisher, Matthew, Kim, Vladimir G., Russell, Bryan C., and Aubry, Mathieu

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape. We demonstrate that the learned elementary 3D structures lead to clear improvements in 3D shape generation and matching. More precisely, we present two complementary approaches for learning elementary structures: (i) patch deformation learning and (ii) point translation learning. Both approaches can be extended to abstract structures of higher dimensions for improved results. We evaluate our method on two tasks: reconstructing ShapeNet objects and estimating dense correspondences between human scans (FAUST inter challenge). We show 16% improvement over surface deformation approaches for shape reconstruction and outperform FAUST inter challenge state of the art by 6%.

Published
2019

2. Unsupervised cycle-consistent deformation for shape matching

Author

Groueix, Thibault, Fisher, Matthew, Kim, Vladimir G., Russell, Bryan C., and Aubry, Mathieu

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

We propose a self-supervised approach to deep surface deformation. Given a pair of shapes, our algorithm directly predicts a parametric transformation from one shape to the other respecting correspondences. Our insight is to use cycle-consistency to define a notion of good correspondences in groups of objects and use it as a supervisory signal to train our network. Our method does not rely on a template, assume near isometric deformations or rely on point-correspondence supervision. We demonstrate the efficacy of our approach by using it to transfer segmentation across shapes. We show, on Shapenet, that our approach is competitive with comparable state-of-the-art methods when annotated training data is readily available, but outperforms them by a large margin in the few-shot segmentation scenario.

Published
2019

3. Photometric Mesh Optimization for Video-Aligned 3D Object Reconstruction

Author

Lin, Chen-Hsuan, Wang, Oliver, Russell, Bryan C., Shechtman, Eli, Kim, Vladimir G., Fisher, Matthew, and Lucey, Simon

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Graphics
Abstract

In this paper, we address the problem of 3D object mesh reconstruction from RGB videos. Our approach combines the best of multi-view geometric and data-driven methods for 3D reconstruction by optimizing object meshes for multi-view photometric consistency while constraining mesh deformations with a shape prior. We pose this as a piecewise image alignment problem for each mesh face projection. Our approach allows us to update shape parameters from the photometric error without any depth or mask information. Moreover, we show how to avoid a degeneracy of zero photometric gradients via rasterizing from a virtual viewpoint. We demonstrate 3D object mesh reconstruction results from both synthetic and real-world videos with our photometric mesh optimization, which is unachievable with either na\"ive mesh generation networks or traditional pipelines of surface reconstruction without heavy manual post-processing., Comment: Accepted to CVPR 2019 (project page & code: https://chenhsuanlin.bitbucket.io/photometric-mesh-optim/)

Published
2019

4. 3D-CODED : 3D Correspondences by Deep Deformation

Author

Groueix, Thibault, Fisher, Matthew, Kim, Vladimir G., Russell, Bryan C., and Aubry, Mathieu

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

We present a new deep learning approach for matching deformable shapes by introducing {\it Shape Deformation Networks} which jointly encode 3D shapes and correspondences. This is achieved by factoring the surface representation into (i) a template, that parameterizes the surface, and (ii) a learnt global feature vector that parameterizes the transformation of the template into the input surface. By predicting this feature for a new shape, we implicitly predict correspondences between this shape and the template. We show that these correspondences can be improved by an additional step which improves the shape feature by minimizing the Chamfer distance between the input and transformed template. We demonstrate that our simple approach improves on state-of-the-art results on the difficult FAUST-inter challenge, with an average correspondence error of 2.88cm. We show, on the TOSCA dataset, that our method is robust to many types of perturbations, and generalizes to non-human shapes. This robustness allows it to perform well on real unclean, meshes from the the SCAPE dataset.

Published
2018

5. AtlasNet: A Papier-M\^ach\'e Approach to Learning 3D Surface Generation

Author

Groueix, Thibault, Fisher, Matthew, Kim, Vladimir G., Russell, Bryan C., and Aubry, Mathieu

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

We introduce a method for learning to generate the surface of 3D shapes. Our approach represents a 3D shape as a collection of parametric surface elements and, in contrast to methods generating voxel grids or point clouds, naturally infers a surface representation of the shape. Beyond its novelty, our new shape generation framework, AtlasNet, comes with significant advantages, such as improved precision and generalization capabilities, and the possibility to generate a shape of arbitrary resolution without memory issues. We demonstrate these benefits and compare to strong baselines on the ShapeNet benchmark for two applications: (i) auto-encoding shapes, and (ii) single-view reconstruction from a still image. We also provide results showing its potential for other applications, such as morphing, parametrization, super-resolution, matching, and co-segmentation.

Published
2018

6. The 3D Jigsaw Puzzle: Mapping Large Indoor Spaces

Author

Martin-Brualla, Ricardo, He, Yanling, Russell, Bryan C., Seitz, Steven M., Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Kobsa, Alfred, Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Fleet, David, editor, Pajdla, Tomas, editor, Schiele, Bernt, editor, and Tuytelaars, Tinne, editor

Published
2014
Full Text
View/download PDF

8. Learning elementary structures for 3D shape generation and matching

Author

Deprelle, Theo, Groueix, Thibault, Fisher, Matthew, Kim, Vladimir G., Russell, Bryan C., Aubry, Mathieu, Laboratoire d'Informatique Gaspard-Monge (LIGM), École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel, imagine [Marne-la-Vallée], Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM)-Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM), Adobe Research, Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS), and Groueix, Thibault

Subjects
FOS: Computer and information sciences, [INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], ComputingMethodologies_COMPUTERGRAPHICS
Abstract

We propose to represent shapes as the deformation and combination of learnable elementary 3D structures, which are primitives resulting from training over a collection of shape. We demonstrate that the learned elementary 3D structures lead to clear improvements in 3D shape generation and matching. More precisely, we present two complementary approaches for learning elementary structures: (i) patch deformation learning and (ii) point translation learning. Both approaches can be extended to abstract structures of higher dimensions for improved results. We evaluate our method on two tasks: reconstructing ShapeNet objects and estimating dense correspondences between human scans (FAUST inter challenge). We show 16% improvement over surface deformation approaches for shape reconstruction and outperform FAUST inter challenge state of the art by 6%.

Published
2021

10. Segmenting Scenes by Matching Image Composites

Author

Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Russell, Bryan C., Efros, Alexei A., Sivic, Josef, Freeman, William T, Zisserman, Andrew, Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Russell, Bryan C., Efros, Alexei A., Sivic, Josef, Freeman, William T, and Zisserman, Andrew

Abstract

In this paper, we investigate how, given an image, similar images sharing the same global description can help with unsupervised scene segmentation. In contrast to recent work in semantic alignment of scenes, we allow an input image to be explainedby partial matches of similar scenes. This allows for a better explanation of the input scenes. We perform MRF-based segmentation that optimizes over matches, while respecting boundary information. The recovered segments are then used to re-query a large database of images to retrieve better matches for the target regions. We show improved performance in detecting the principal occluding and contact boundaries for the scene over previous methods on data gathered from the LabelMe database., United States. Office of Naval Research. Multidisciplinary University Research Initiative (N00014-06-1-0734, N00014-07-1-0182), United States. Office of Naval Research. National Geospatial-Intelligence Agency (NEGI-1582-04-0004), National Science Foundation (U.S.) (Grant IIS-0546547)

Published
2021

11. Segmenting Scenes by Matching Image Composites

Author

Russell, Bryan C., Efros, Alexei A., Sivic, Josef, Freeman, William T., Zisserman, Andrew, Russell, Bryan C., Efros, Alexei A., Sivic, Josef, Freeman, William T., and Zisserman, Andrew

Abstract

In this paper, we investigate how, given an image, similar images sharing the same global description can help with unsupervised scene segmentation. In contrast to recent work in semantic alignment of scenes, we allow an input image to be explainedby partial matches of similar scenes. This allows for a better explanation of the input scenes. We perform MRF-based segmentation that optimizes over matches, while respecting boundary information. The recovered segments are then used to re-query a large database of images to retrieve better matches for the target regions. We show improved performance in detecting the principal occluding and contact boundaries for the scene over previous methods on data gathered from the LabelMe database.

Published
2021

16. Where was this picture painted ? - Localizing paintings by alignment to 3D models

Author

Aubry, Mathieu, Russell, Bryan C., Sivic, Josef, Models of visual object recognition and scene understanding (WILLOW), Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Paris-Rocquencourt, Institut National de Recherche en Informatique et en Automatique (Inria), Science and Technology Center for Visual Computing, INTEL, Intel-Intel, Laboratoire d'informatique de l'école normale supérieure (LIENS), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS), Département d'informatique de l'École normale supérieure (DI-ENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Inria Paris-Rocquencourt, and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)

Subjects
Reconaissance, analyse 3D, localisation, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Abstract

National audience; Cet article présente une technique qui peut de manière fiable aligner une représentation non photo-réaliste d'un site architectural, tel un dessin ou une peinture, avec un model 3D du site. Pour ce faire, nous représentons le model 3D par un ensemble d'éléments discriminatifs qui sont automatiquement découverts dans des vues du modèle. Nous montrons que les éléments trouvés sont reliés de manière robuste aux changements de style (aquarelle, croquis, photographies anciennes) et aux différences structurelles. D'avantage de détails sur notre méthode et une évaluation plus détaillée est disponible [1].

Published
2014

17. Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models

Author

Aubry, Mathieu, Maturana, Daniel, Efros, Alexei, Russell, Bryan C., Sivic, Josef, Laboratoire d'Informatique Gaspard-Monge (LIGM), Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS), École des Ponts ParisTech (ENPC), imagine [Marne-la-Vallée], Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Est Marne-la-Vallée (UPEM)-École des Ponts ParisTech (ENPC)-ESIEE Paris-Fédération de Recherche Bézout-Centre National de la Recherche Scientifique (CNRS)-Centre Scientifique et Technique du Bâtiment (CSTB), Models of visual object recognition and scene understanding (WILLOW), Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Paris-Rocquencourt, Institut National de Recherche en Informatique et en Automatique (Inria), Carnegie Mellon University [Pittsburgh] (CMU), Lawrence Berkeley National Laboratory [Berkeley] (LBNL), Intel Research Laboratory, Intel, Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM), Centre Scientifique et Technique du Bâtiment (CSTB)-École des Ponts ParisTech (ENPC)-Laboratoire d'Informatique Gaspard-Monge (LIGM), Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM)-Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-Université Paris-Est Marne-la-Vallée (UPEM), Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Inria Paris-Rocquencourt, Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM)-Centre National de la Recherche Scientifique (CNRS)-Fédération de Recherche Bézout-ESIEE Paris-École des Ponts ParisTech (ENPC)-Université Paris-Est Marne-la-Vallée (UPEM)-Centre Scientifique et Technique du Bâtiment (CSTB), Département d'informatique de l'École normale supérieure (DI-ENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), and Aubry, Mathieu

Subjects
[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Abstract

International audience; This paper poses object category detection in images as a type of 2D-to-3D alignment problem, utilizing the large quantities of 3D CAD models that have been made publicly available online. Using the "chair" class as a running example, we propose an exemplar-based 3D category representation, which can explicitly model chairs of different styles as well as the large variation in viewpoint. We develop an approach to establish part-based correspondences between 3D CAD models and real photographs. This is achieved by (i) representing each 3D model using a set of view-dependent mid-level visual elements learned from synthesized views in a discriminative fashion, (ii) carefully calibrating the individual element detectors on a common dataset of negative images, and (iii) matching visual elements to the test image allowing for small mutual deformations but preserving the viewpoint and style constraints. We demonstrate the ability of our system to align 3D models with 2D objects in the challenging PASCAL VOC images, which depict a wide variety of chairs in complex scenes.

Published
2014

21. Segmenting Scenes by Matching Image Composites

Author

Russell, Bryan C., Efros, Alexei, Sivic, Josef, Freeman, William T., and Zisserman, Andrew

Subjects
FOS: Computer and information sciences, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 80101 Adaptive Agents and Intelligent Robotics
Abstract

In this paper, we investigate how, given an image, similar images sharing the same global description can help with unsupervised scene segmentation. In contrast to recent work in semantic alignment of scenes, we allow an input image to be explained by partial matches of similar scenes. This allows for a better explanation of the input scenes. We perform MRF-based segmentation that optimizes over matches, while respecting boundary information. The recovered segments are then used to re-query a large database of images to retrieve better matches for the target regions. We show improved performance in detecting the principal occluding and contact boundaries for the scene over previous methods on data gathered from the LabelMe database.

Published
2009
Full Text
View/download PDF

22. 3D Wikipedia.

Author

Russell, Bryan C., Martin-Brualla, Ricardo, Butler, Daniel J., Seitz, Steven M., and Zettlemoyer, Luke

Subjects
THREE-dimensional imaging, TOURIST attractions, VISUALIZATION, NATURAL language processing, RENDERING (Computer graphics)
Abstract

We introduce an approach for analyzing Wikipedia and other text, together with online photos, to produce annotated 3D models of famous tourist sites. The approach is completely automated, and leverages online text and photo co-occurrences via Google Image Search. It enables a number of new interactions, which we demonstrate in a new 3D visualization tool. Text can be selected to move the camera to the corresponding objects, 3D bounding boxes provide anchors back to the text describing them, and the overall narrative of the text provides a temporal guide for automatically flying through the scene to visualize the world as you read about it. We show compelling results on several major tourist sites. [ABSTRACT FROM AUTHOR]

Published
2017
Full Text
View/download PDF

23. Basic level scene understanding: from labels to structure and beyond

Author

Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Xiao, Jianxiong, Ehinger, Krista A., Oliva, Aude, Torralba, Antonio, Russell, Bryan C., Hays, James, Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Xiao, Jianxiong, Ehinger, Krista A., Oliva, Aude, Torralba, Antonio, Russell, Bryan C., and Hays, James

Abstract

An early goal of computer vision was to build a system that could automatically understand a 3D scene just by looking. This requires not only the ability to extract 3D information from image information alone, but also to handle the large variety of different environments that comprise our visual world. This paper summarizes our recent efforts toward these goals. First, we describe the SUN database, which is a collection of annotated images spanning 908 different scene categories. This database allows us to systematically study the space of possible everyday scenes and to establish a benchmark for scene and object recognition. We also explore ways of coping with the variety of viewpoints within these scenes. For this, we have introduced a database of 360° panoramic images for many of the scene categories in the SUN database and have explored viewpoint recognition within the environments. Finally, we describe steps toward a unified 3D parsing of everyday scenes: (i) the ability to localize geometric primitives in images, such as cuboids and cylinders, which often comprise many everyday objects, and (ii) an integrated system to extract the 3D structure of the scene and objects depicted in an image., National Science Foundation (U.S.) (Grant 1016862), Google (Firm) (Research Award), United States. Office of Naval Research. Multidisciplinary University Research Initiative (N000141010933), National Science Foundation (U.S.) (Career Award 0747120)

Published
2014

26. LabelMe: Online image annotation and applications

Author

Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Torralba, Antonio, Yuen, Jenny, Russell, Bryan C., Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Torralba, Antonio, Yuen, Jenny, and Russell, Bryan C.

Abstract

Central to the development of computer vision systems is the collection and use of annotated images spanning our visual world. Annotations may include information about the identity, spatial extent, and viewpoint of the objects present in a depicted scene. Such a database is useful for the training and evaluation of computer vision systems. Motivated by the availability of images on the Internet, we introduced a web-based annotation tool that allows online users to label objects and their spatial extent in images. To date, we have collected over 400 000 annotations that span a variety of different scene and object classes. In this paper, we show the contents of the database, its growth over time, and statistics of its usage. In addition, we explore and survey applications of the database in the areas of computer vision and computer graphics. Particularly, we show how to extract the real-world 3-D coordinates of images in a variety of scenes using only the user-provided object annotations. The output 3-D information is comparable to the quality produced by a laser range scanner. We also characterize the space of the images in the database by analyzing 1) statistics of the co-occurrence of large objects in the images and 2) the spatial layout of the labeled images., National Science Foundation (U.S.) (Career award IIS 0747120), National Defense Science and Engineering Graduate Fellowship

Published
2011

27. Building a database of 3D scenes from user annotations

Author

Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Torralba, Antonio, Russell, Bryan C., Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Torralba, Antonio, and Russell, Bryan C.

Abstract

In this paper, we wish to build a high quality database of images depicting scenes, along with their real-world three-dimensional (3D) coordinates. Such a database is useful for a variety of applications, including training systems for object detection and validation of 3D output. We build such a database from images that have been annotated with only the identity of objects and their spatial extent in images. Important for this task is the recovery of geometric information that is implicit in the object labels, such as qualitative relationships between objects (attachment, support, occlusion) and quantitative ones (inferring camera parameters). We describe a model that integrates cues extracted from the object labels to infer the implicit geometric information. We show that we are able to obtain high quality 3D information by evaluating the proposed approach on a database obtained with a laser range scanner. Finally, given the database of 3D scenes, we show how it can find better scene matches for an unlabeled image by expanding the database through viewpoint interpolation to unseen views., National Science Foundation (U.S.) (CAREER award IIS 0747120)

Published
2010

28. 3D Wikipedia

Author

Russell, Bryan C., primary, Martin-Brualla, Ricardo, additional, Butler, Daniel J., additional, Seitz, Steven M., additional, and Zettlemoyer, Luke, additional

Published
2013
Full Text
View/download PDF

30. LabelMe: a database and web-based tool for image annotation

Author

Russell, Bryan C., Torralba, Antonio, Murphy, Kevin P., Freeman, William T., Russell, Bryan C., Torralba, Antonio, Murphy, Kevin P., and Freeman, William T.

Abstract

Research in object detection and recognition in cluttered scenes requires large image collections with ground truth labels. The labels should provide information about the object classes present in each image, as well as their shape and locations, and possibly other attributes such as pose. Such data is useful for testing, as well as for supervised learning. This project provides a web-based annotation tool that makes it easy to annotate images, and to instantly sharesuch annotations with the community. This tool, plus an initial set of 10,000 images (3000 of which have been labeled), can be found at http://www.csail.mit.edu/$\sim$brussell/research/LabelMe/intro.html

Published
2005

31. Discovering object categories in image collections

Author

Sivic, Josef, Russell, Bryan C., Efros, Alexei A., Zisserman, Andrew, Freeman, William T., Sivic, Josef, Russell, Bryan C., Efros, Alexei A., Zisserman, Andrew, and Freeman, William T.

Abstract

Given a set of images containing multiple object categories,we seek to discover those categories and their image locations withoutsupervision. We achieve this using generative modelsfrom the statistical text literature: probabilistic Latent SemanticAnalysis (pLSA), and Latent Dirichlet Allocation (LDA). In text analysisthese are used to discover topics in a corpus using the bag-of-wordsdocument representation. Here we discover topics as object categories, sothat an image containing instances of several categories is modelled as amixture of topics.The models are applied to images by using avisual analogue of a word, formed by vector quantizing SIFT like regiondescriptors. We investigate a set of increasingly demanding scenarios,starting with image sets containing only two object categories through tosets containing multiple categories (including airplanes, cars, faces,motorbikes, spotted cats) and background clutter. The object categoriessample both intra-class and scale variation, and both the categories andtheir approximate spatial layout are found without supervision.We also demonstrate classification of unseen images and images containingmultiple objects. Performance of the proposed unsupervised method is compared tothe semi-supervised approach of Fergus et al.

Published
2005

32. Basic level scene understanding

Author

Xiao, Jianxiong, primary, Russell, Bryan C., additional, Hays, James, additional, Ehinger, Krista A., additional, Oliva, Aude, additional, and Torralba, Antonio, additional

Published
2012
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results