Peter V. Gehler

On feature combination for multiclass object classification

A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. While this is a necessity in order to generalize beyond a given set of training images, it is also a very difficult problem due to the high variability of visual appearance within each class. In the last years substantial performance gains on challenging benchmark datasets have been reported in the literature. This progress can be attributed to two developments: the design of highly discriminative and robust image features and the combination of multiple complementary features based on different aspects such as shape, color or texture. In this paper we study several models that aim at learning the correct weighting of different features from training data. These include multiple kernel learning as well as simple baseline methods. Furthermore we derive ensemble methods inspired by Boosting which are easily extendable to several multiclass setting. All methods are thoroughly evaluated on object classification datasets using a multitude of feature descriptors. The key results are that even very simple baseline methods, that are orders of magnitude faster than learning techniques are highly competitive with multiple kernel learning. Furthermore the Boosting type methods are found to produce consistently better results in all experiments. We provide insight of when combination methods can be expected to work and how the benefit of complementary features can be exploited most efficiently.

Bayesian color constancy revisited

Computational color constancy is the task of estimating the true reflectances of visible surfaces in an image. In this paper we follow a line of research that assumes uniform illumination of a scene, and that the principal step in estimating reflectances is the estimation of the scene illuminant. We review recent approaches to illuminant estimation, firstly those based on formulae for normalisation of the reflectance distribution in an image - so-called grey-world algorithms, and those based on a Bayesian formulation of image formation. In evaluating these previous approaches we introduce a new tool in the form of a database of 568 high-quality, indoor and outdoor images, accurately labelled with illuminant, and preserved in their raw form, free of correction or normalisation. This has enabled us to establish several properties experimentally. Firstly automatic selection of grey-world algorithms according to image properties is not nearly so effective as has been thought. Secondly, it is shown that Bayesian illuminant estimation is significantly improved by the improved accuracy of priors for illuminant and reflectance that are obtained from the new dataset.

Teaching 3D geometry to deformable part models

Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the detection of individual objects, higher-level applications such as 3D scene understanding or 3D object tracking would benefit from more fine-grained object hypotheses incorporating 3D geometric information, such as viewpoints or the locations of individual parts. In this paper, we help narrowing the representational gap between the ideal input of a scene understanding system and object class detector output, by designing a detector particularly tailored towards 3D geometric reasoning. In particular, we extend the successful discriminatively trained deformable part models to include both estimates of viewpoint and 3D parts that are consistent across viewpoints. We experimentally verify that adding 3D geometric information comes at minimal performance loss w.r.t. 2D bounding box localization, but outperforms prior work in 3D viewpoint estimation and ultra-wide baseline matching.

Poselet Conditioned Pictorial Structures

In this paper we consider the challenging problem of articulated human pose estimation in still images. We observe that despite high variability of the body articulations, human motions and activities often simultaneously constrain the positions of multiple body parts. Modelling such higher order part dependencies seemingly comes at a cost of more expensive inference, which resulted in their limited use in state-of-the-art methods. In this paper we propose a model that incorporates higher order part dependencies while remaining efficient. We achieve this by defining a conditional model in which all body parts are connected a-priori, but which becomes a tractable tree-structured pictorial structures model once the image observations are available. In order to derive a set of conditioning variables we rely on the poselet-based features that have been shown to be effective for people detection but have so far found limited application for articulated human pose estimation. We demonstrate the effectiveness of our approach on three publicly available pose estimation benchmarks improving or being on-par with state of the art in each case.

DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation

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.

Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image

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.

Occlusion Patterns for Object Class Detection

Despite the success of recent object class recognition systems, the long-standing problem of partial occlusion remains a major challenge, and a principled solution is yet to be found. In this paper we leave the beaten path of methods that treat occlusion as just another source of noise - instead, we include the occluder itself into the modelling, by mining distinctive, reoccurring occlusion patterns from annotated training data. These patterns are then used as training data for dedicated detectors of varying sophistication. In particular, we evaluate and compare models that range from standard object class detectors to hierarchical, part-based representations of occluder/occludee pairs. In an extensive evaluation we derive insights that can aid further developments in tackling the occlusion challenge.

On parameter learning in CRF-based approaches to object class image segmentation

Recent progress in per-pixel object class labeling of natural images can be attributed to the use of multiple types of image features and sound statistical learning approaches. Within the latter, Conditional Random Fields (CRF) are prominently used for their ability to represent interactions between random variables. Despite their popularity in computer vision, parameter learning for CRFs has remained difficult, popular approaches being cross-validation and piecewise training. In this work, we propose a simple yet expressive tree-structured CRF based on a recent hierarchical image segmentation method. Our model combines and weights multiple image features within a hierarchical representation and allows simple and efficient globally-optimal learning of ≅ 105 parameters. The tractability of our model allows us to pose and answer some of the open questions regarding parameter learning applying to CRF-based approaches. The key findings for learning CRF models are, from the obvious to the surprising, i) multiple image features always help, ii) the limiting dimension with respect to current models is the amount of training data, iii) piecewise training is competitive, iv) current methods for max-margin training fail for models with many parameters.

3D 2 PM - 3d deformable part models

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, 2D feature-based models are the predominant paradigm in object recognition today. While such models have shown competitive bounding box (BB) detection performance, they are clearly limited in their capability of fine-grained reasoning in 3D or continuous viewpoint estimation as required for advanced tasks such as 3D scene understanding. This work extends the deformable part model [1] to a 3D object model. It consists of multiple parts modeled in 3D and a continuous appearance model. As a result, the model generalizes beyond BB oriented object detection and can be jointly optimized in a discriminative fashion for object detection and viewpoint estimation. Our 3D Deformable Part Model (3D2PM) leverages on CAD data of the object class, as a 3D geometry proxy.

Scene carving: scene consistent image retargeting

Image retargeting algorithms often create visually disturbing distortion. We introduce the property of scene consistency, which is held by images which contain no object distortion and have the correct object depth ordering. We present two new image retargeting algorithms that preserve scene consistency. These algorithms make use of a user-provided relative depth map, which can be created easily using a simple GrabCut-style interface. Our algorithms generalize seam carving. We decompose the image retargeting procedure into (a) removing image content with minimal distortion and (b) re-arrangement of known objects within the scene to maximize their visibility. Our algorithms optimize objectives (a) and (b) jointly. However, they differ considerably in how they achieve this. We discuss this in detail and present examples illustrating the rationale of preserving scene consistency in retargeting.