Estimating 2D human pose is hard because people appear in a wide range of poses and have varying body shape. They wear varied clothing and the articulation results in significant self occlusion. We have developed several state-of-the-art methods to address these problems.
Human pose estimation, 3D mesh registration and action recognition techniques have made significant progress during the last years. However, most existing datasets to evaluate them are inadequate for capturing the challenges of real-world scenarios. We introduce novel datasets and benchmarks, all publicly av...
A long standing and conceptually elegant view of computer vision is to use a generative model of the physical image formation process and posterior inference to infer or explain the image observations. A key problem in this inverse graphics view is the difficulty of posterior inference at run time. This diffi...
Intrinsic images such as albedo and shading are valuable for later stages of visual processing. Previous methods for extracting albedo and shading use either single images or images together with depth data. Instead, we defineintrinsic video estimation as the problem of extracting temporally coherent albedo and shading...
The ability to recognize and categorize objects in any type of visual scene is an integral part of scene recognition systems. While for constrained scenarios, like face detection, this problem has largely been solved, the general case of recognizing any kind of object in real world and cluttered environments remains an open res...
Holistic scene understanding is an important prerequisite for many indoor and outdoor applications, including autonomous driving, navigation, indoor and outdoor mapping as well as localization. Given a high-dimension input (e.g., image or video stream), the task is to extract a rich but compact representation that is easily acc...
The problem of decomposing an image into its different intrinsic layers, such as shading, reflectance, and shape components, is one of the fundamental problems of computer vision. We believe that many computer vision tasks will benefit from having access to such separations. As an example, object detection should benefit from factor...
Most problems that we encounter in computer vision can naturally be understood as structured prediction problems. To describe the world around us we need rich representations, and these representations have interesting interdependencies. As an example consider scene understanding. The 3D geometry of a scene, the composition of objec...
ACM Multimedia Open Source Software Competition, ACM OSSC16, October 2016 (proceedings) Accepted
The caffe framework is one of the leading deep learning toolboxes in the machine learning and computer vision community. While it offers efficiency and configurability, it falls short of a full interface to Python. With increasingly involved procedures for training deep networks and reaching depths of hundreds of layers, creating configuration files and keeping them consistent becomes an error prone process.
We introduce the barrista framework, offering full, pythonic control over caffe. It separates responsibilities and offers code to solve frequently occurring tasks for pre-processing, training and model inspection. It is compatible to all caffe versions since mid 2015 and can import and export .prototxt files.
Examples are included, e.g., a deep residual network implemented in only 172 lines (for arbitrary depths), comparing to 2320 lines in the official implementation for the equivalent model.
In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, Springer, October 2016 (inproceedings)
In this paper we propose a CNN architecture for semantic image segmentation. We introduce a new “bilateral inception” module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image. The feature spaces for bilateral filtering and other parameters of the module are learned end-to-end using standard backpropagation techniques. The bilateral inception module addresses two issues that arise with general CNN segmentation architectures. First, this module propagates information between (super) pixels while respecting image edges, thus using the structured information of the problem for improved results. Second, the layer recovers a full resolution segmentation result from the lower resolution solution of a CNN. In the experiments, we modify several existing CNN architectures by inserting our inception modules between the last CNN (1 × 1 convolution) layers. Empirical results on three different datasets show reliable improvements not only in comparison to the baseline networks, but also in comparison to several dense-pixel prediction techniques such as CRFs, while being competitive in time.
In Computer Vision – ECCV 2016, Lecture Notes in Computer Science, Springer International Publishing, October 2016 (inproceedings)
We describe the first method to automatically estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image. We estimate a full 3D mesh and show that 2D joints alone carry a surprising amount of information about body shape. The problem is challenging because of the complexity of the human body, articulation, occlusion, clothing, lighting, and the inherent ambiguity in inferring 3D from 2D. To solve this, we first use a recently published CNN-based method, DeepCut, to predict (bottom-up) the 2D body joint locations. We then fit (top-down) a recently published statistical body shape model, called SMPL, to the 2D joints. We do so by minimizing an objective function that penalizes the error between the projected 3D model joints and detected 2D joints. Because SMPL captures correlations in human shape across the population, we are able to robustly fit it to very little data. We further leverage the 3D model to prevent solutions that cause interpenetration. We evaluate our method, SMPLify, on the Leeds Sports, HumanEva, and Human3.6M datasets, showing superior
pose accuracy with respect to the state of the art.
Pishchulin, L., Insafutdinov, E., Tang, S., Andres, B., Andriluka, M., Gehler, P., Schiele, B.
In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June 2016 (inproceedings)
This paper considers the task of articulated human pose estimation of multiple people in real-world images. We propose an approach that jointly solves the tasks of detection and pose estimation: it infers the number of persons in a scene, identifies occluded body parts, and disambiguates body parts between people in close proximity of each other.
This joint formulation is in contrast to previous strategies, that address the problem by first detecting people and subsequently estimating their body pose. We propose a partitioning and labeling formulation of a set of body-part hypotheses generated with CNN-based part detectors. Our formulation, an instance of an integer linear program, implicitly performs non-maximum suppression on the set of part candidates and groups them to form configurations of body parts respecting geometric and appearance constraints. Experiments on four different datasets demonstrate state-of-the-art results for both single person and multi person pose estimation.
In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 4452-4461, June 2016 (inproceedings)
Bilateral filters have wide spread use due to their edge-preserving properties. The common use case is to manually choose a parametric filter type, usually a Gaussian filter. In this paper, we will generalize the parametrization and in particular derive a gradient descent algorithm so the filter parameters can be learned from data. This derivation allows to learn high dimensional linear filters that operate in sparsely populated feature spaces. We build on the permutohedral lattice construction for efficient filtering. The ability to learn more general forms of high-dimensional filters can be used in several diverse applications. First, we demonstrate the use in applications where single filter applications are desired for runtime reasons. Further, we show how this algorithm can be used to learn the pairwise potentials in densely connected conditional random fields and apply these to different image segmentation tasks. Finally, we introduce layers of bilateral filters in CNNs and propose bilateral neural networks for the use of high-dimensional sparse data. This view provides new ways to encode model structure into network architectures. A diverse set of experiments empirically validates the usage of general forms of filters.
Pattern Analysis and Machine Intelligence, 37(11):14, IEEE, March 2015 (article)
As objects are inherently 3-dimensional, they have been modeled in 3D in the early days of computer vision. Due to the ambiguities arising from mapping 2D features to 3D models, 3D object representations have been neglected and 2D feature-based models are the predominant paradigm in object detection nowadays. While such models have achieved outstanding bounding box detection performance, they come with limited expressiveness, as they are clearly limited in their capability of reasoning about 3D shape or viewpoints. In this work, we bring the worlds of 3D and 2D object representations closer, by building an object detector which leverages the expressive power of 3D object representations while at the same time can be robustly matched to image evidence. To that end, we gradually extend the successful deformable part model  to include viewpoint information and part-level 3D geometry information, resulting in several different models with different level of expressiveness. We end up with a 3D object model, consisting of multiple object parts represented in 3D and a continuous appearance model. We experimentally verify that our models, while providing richer object hypotheses than the 2D object models, provide consistently better joint object localization and viewpoint estimation than the state-of-the-art multi-view and 3D object detectors on various benchmarks (KITTI , 3D object classes , Pascal3D+ , Pascal VOC 2007 , EPFL multi-view cars ).
This paper presents a convolutional layer that is able to process sparse input features. As an example, for image recognition problems this allows an efficient filtering of signals that do not lie on a dense grid (like pixel position), but of more general features (such as color values). The presented algorithm makes use of the permutohedral lattice data structure. The permutohedral lattice was introduced to efficiently implement a bilateral filter, a commonly used image processing operation. Its use allows for a generalization of the convolution type found in current (spatial) convolutional network architectures.
In Applications of Computer Vision (WACV), 2015 IEEE Winter Conference on, pages: 1038-1045, IEEE, January 2015 (inproceedings)
In this paper we propose a system for the problem of facade segmentation. Building facades are highly structured images and consequently most methods that have been proposed for this problem, aim to make use of this strong prior information. We are describing a system that is almost domain independent and consists of standard segmentation methods. A sequence of boosted decision trees is stacked using auto-context features and learned using the stacked generalization technique. We find that this, albeit standard, technique performs better, or equals, all previous published empirical results on all available facade benchmark datasets. The proposed method is simple to implement, easy to extend, and very efficient at test time inference.
In Computer Vision and Image Understanding, Special Issue on Generative Models in Computer Vision and Medical Imaging, 136, pages: 32-44, Elsevier, July 2015 (inproceedings)
Computer vision is hard because of a large variability in lighting, shape, and texture; in addition the image signal is non-additive due to occlusion. Generative models promised to account for this variability by accurately modelling the image formation process as a function of latent variables with prior beliefs. Bayesian posterior inference could then, in principle, explain the observation. While intuitively appealing, generative models for computer vision have largely failed to deliver on that promise due to the difficulty of posterior inference. As a result the community has favored efficient discriminative approaches. We still believe in the usefulness of generative models in computer vision, but argue that we need to leverage existing discriminative or even heuristic computer vision methods.
We implement this idea in a principled way in our informed sampler and in careful experiments demonstrate it on challenging models which contain renderer programs as their components. The informed sampler, using simple discriminative proposals based on existing computer vision technology achieves dramatic improvements in inference. Our approach enables a new richness in generative models that was out of reach with existing inference technology.
In Computer Vision – ECCV 2014, 8690, pages: 360-375, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, September 2014 (inproceedings)
Intrinsic images such as albedo and shading are valuable for later stages of visual processing. Previous methods for extracting albedo and shading use either single images or images together with depth data. Instead, we define intrinsic video estimation as the problem of extracting temporally coherent albedo and shading from video alone. Our approach exploits the assumption that albedo is constant over time while shading changes slowly. Optical flow aids in the accurate estimation of intrinsic video by providing temporal continuity as well as putative surface boundaries. Additionally, we find that the estimated albedo sequence can be used to improve optical flow accuracy in sequences with changing illumination. The approach makes only weak assumptions about the scene and we show that it substantially outperforms existing single-frame intrinsic image methods. We evaluate this quantitatively on synthetic sequences as well on challenging natural sequences with complex geometry, motion, and illumination.
Kong, N., Gehler, P., Black, M. J.
In Computer Vision – ECCV 2014, 8690, pages: 360-375, Lecture Notes in Computer Science, (Editors: D. Fleet and T. Pajdla and B. Schiele and T. Tuytelaars ), Springer International Publishing, September 2014 (inproceedings)
In Computer Vision – ECCV 2014, LNCS 8693, pages: 331-346, Lecture Notes in Computer Science, (Editors: Fleet, David and Pajdla, Tomas and Schiele, Bernt and Tuytelaars, Tinne), Springer, September 2014 (inproceedings)
This paper proposes a new formulation of the human pose estimation problem. We present the Fields of Parts model, a binary Conditional Random Field model designed to detect human body parts of articulated people in single images.
The Fields of Parts model is inspired by the idea of Pictorial Structures, it models local appearance and joint spatial configuration of the human body. However the underlying graph structure is entirely different. The idea is simple: we model the presence and absence of a body part at every possible position, orientation, and scale in an image with a binary random variable. This results into a vast number of random variables, however, we show that approximate inference in this model is efficient. Moreover we can encode the very same appearance and spatial structure as in Pictorial Structures models.
This approach allows us to combine ideas from segmentation and pose estimation into a single model. The Fields of Parts model can use evidence from the background, include local color information, and it is connected more densely than a kinematic chain structure. On the challenging Leeds Sports Poses dataset we improve over the Pictorial Structures counterpart by 5.5% in terms of Average Precision of Keypoints (APK).
Advanced Structured Prediction, pages: 432, Neural Information Processing Series, MIT Press, November 2014 (book)
The goal of structured prediction is to build machine learning models that predict relational information that itself has structure, such as being composed of multiple interrelated parts. These models, which reflect prior knowledge, task-specific relations, and constraints, are used in fields including computer vision, speech recognition, natural language processing, and computational biology. They can carry out such tasks as predicting a natural language sentence, or segmenting an image into meaningful components.
These models are expressive and powerful, but exact computation is often intractable. A broad research effort in recent years has aimed at designing structured prediction models and approximate inference and learning procedures that are computationally efficient. This volume offers an overview of this recent research in order to make the work accessible to a broader research community. The chapters, by leading researchers in the field, cover a range of topics, including research trends, the linear programming relaxation approach, innovations in probabilistic modeling, recent theoretical progress, and resource-aware learning.
International Conference on Learning Representations, April 2014 (conference)
While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer output require larger amounts of training data, preferably well covering the relevant aspects such as viewpoint and fine-grained categories. In this paper, we address this issue from the perspective of transfer learning, and design an object class model that explicitly leverages correlations between visual features. Specifically, our model represents prior distributions over permissible multi-view detectors in a parametric way -- the priors are learned once from training data of a source object class, and can later be used to facilitate the learning of a detector for a target class. As we show in our experiments, this transfer is not only beneficial for detectors based on basic-level category representations, but also enables the robust learning of detectors that represent classes at finer levels of granularity, where training data is typically even scarcer and more unbalanced. As a result, we report largely improved performance in simultaneous 2D object localization and viewpoint estimation on a recent dataset of challenging street scenes.
In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 1314-1321, IEEE, June 2014 (inproceedings)
Dynamic Bayesian networks such as Hidden Markov
Models (HMMs) are successfully used as probabilistic models
for human motion. The use of hidden variables makes
them expressive models, but inference is only approximate
and requires procedures such as particle filters or Markov
chain Monte Carlo methods. In this work we propose to instead
use simple Markov models that only model observed
quantities. We retain a highly expressive dynamic model by
using interactions that are nonlinear and non-parametric.
A presentation of our approach in terms of latent variables
shows logarithmic growth for the computation of exact loglikelihoods
in the number of latent states. We validate
our model on human motion capture data and demonstrate
state-of-the-art performance on action recognition and motion
International Journal of Computer Vision, Springer, December 2013 (article)
Ranking hypothesis sets is a powerful concept for efficient object detection. In this work, we propose a branch&rank scheme that detects objects with often less than 100 ranking operations. This efficiency enables the use of strong and also costly classifiers like non-linear SVMs with RBF-TeX kernels. We thereby relieve an inherent limitation of branch&bound methods as bounds are often not tight enough to be effective in practice. Our approach features three key components: a ranking function that operates on sets of hypotheses and a grouping of these into different tasks. Detection efficiency results from adaptively sub-dividing the object search space into decreasingly smaller sets. This is inherited from branch&bound, while the ranking function supersedes a tight bound which is often unavailable (except for rather limited function classes). The grouping makes the system effective: it separates image classification from object recognition, yet combines them in a single formulation, phrased as a structured SVM problem. A novel aspect of branch&rank is that a better ranking function is expected to decrease the number of classifier calls during detection. We use the VOC’07 dataset to demonstrate the algorithmic properties of branch&rank.
In Proceedings IEEE Conf. on Computer Vision (ICCV), pages: 1281-1288, December 2013 (inproceedings)
Having a sensible prior of human pose is a vital ingredient for many computer vision applications, including tracking and pose estimation. While the application of global non-parametric approaches and parametric models has led to some success, finding the right balance in terms of flexibility and tractability, as well as estimating model parameters from data has turned out to be challenging. In this work, we introduce a sparse Bayesian network model of human pose that is non-parametric with respect to the estimation of both its graph structure and its local distributions. We describe an efficient sampling scheme for our model and show its tractability for the computation of exact log-likelihoods. We empirically validate our approach on the Human 3.6M dataset and demonstrate superior performance to global models and parametric networks. We further illustrate our model's ability to represent and compose poses not present in the training set (compositionality) and describe a speed-accuracy trade-off that allows realtime scoring of poses.
Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.
In International Conference on Computer Vision (ICCV), pages: 3487 - 3494 , IEEE, December 2013 (inproceedings)
Typical approaches to articulated pose estimation combine spatial modelling of the human body with appearance modelling of body parts. This paper aims to push the state-of-the-art in articulated pose estimation in two ways. First we explore various types of appearance representations aiming to substantially improve the body part hypotheses. And second, we draw on and combine several recently proposed powerful ideas such as more flexible spatial models as well as image-conditioned spatial models. In a series of experiments we draw several important conclusions: (1) we show that the proposed appearance representations are complementary; (2) we demonstrate that even a basic tree-structure spatial human body model achieves state-of-the-art performance when augmented with the proper appearance representation; and (3) we show that the combination of the best performing appearance model with a flexible image-conditioned spatial model achieves the best result, significantly improving over the state of the art, on the "Leeds Sports Poses'' and "Parse'' benchmarks.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems