Non-planar object deformations result in challenging but informative signal variations. We aim to recover this information in a feedforward manner by employing discriminatively trained convolutional networks. We formulate the task as a regression problem and train our networks by leveraging upon manually annotated correspondences between images and 3D surfaces. In this talk, the focus will be on our recent work "DensePose", where we form the "COCO-DensePose" dataset by introducing an efficient annotation pipeline to collect correspondences between 50K persons appearing in the COCO dataset and the SMPL 3D deformable human-body model. We use our dataset to train CNN-based systems that deliver dense correspondences 'in the wild', namely in the presence of background, occlusions, multiple objects and scale variations. We experiment with fully-convolutional networks and region-based DensePose-RCNN model and observe a superiority of the latter; we further improve accuracy through cascading, obtaining a system that delivers highly accurate results in real time (http://densepose.org).
Organizers: Georgios Pavlakos
Two talks for the price of one! I will present my recent work on the challenging problem of stereo matching of scenes with little or no surface texture, attacking the problem from two very different angles. First, I will discuss how surface orientation priors can be added to the popular semi-global matching (SGM) algorithm, which significantly reduces errors on slanted weakly-textured surfaces. The orientation priors serve as a soft constraint during matching and can be derived in a variety of ways, including from low-resolution matching results and from monocular analysis and Manhattan-world assumptions. Second, we will examine the pathological case of Mondrian Stereo -- synthetic scenes consisting solely of solid-colored planar regions, resembling paintings by Piet Mondrian. I will discuss assumptions that allow disambiguating such scenes, present a novel stereo algorithm employing symbolic reasoning about matched edge segments, and discuss how similar ideas could be utilized in robust real-world stereo algorithms for untextured environments.
Organizers: Anurag Ranjan
Humans act upon their environment through motion, the ability to plan their movements is therefore an essential component of their autonomy. In recent decades, motion planning has been widely studied in robotics and computer graphics. Nevertheless robots still fail to achieve human reactivity and coordination. The need for more efficient motion planning algorithms has been present through out my own research on "human-aware" motion planning, which aims to take the surroundings humans explicitly into account. I believe imitation learning is the key to this particular problem as it allows to learn both, new motion skills and predictive models, two capabilities that are at the heart of "human-aware" robots while simultaneously holding the promise of faster and more reactive motion generation. In this talk I will present my work in this direction.
We present an approach to creating 3D models of objects depicted in Web images, even when each object may only be shown in a single image. Our approach uses a comparatively small collection of existing 3D models to guide the reconstruction process. These existing shapes are used to derive information about shape structure. Our guiding idea is to jointly analyze the images and the available 3D models. Joint analysis of all images along with the available shapes regularizes the formulated optimization problems, stabilizes estimation of camera parameters and construction of dense pixel-level correspondences, and leads to reasonable reproduction of object appearance in the absence of traditional multi-view cues. Joint work with Qixing Huang and Hai Wang.
Image-based rendering has been introduced in the 1990s as an alternative approach to photorealistic rendering. Its key idea is to novel renderings by re-projecting pixels from nearby views. The basic approach works well for many scenes but breaks down if the scene contains “non-standard” elements such as reflective surfaces. In this talk, I will first show how we can extend image-based rendering to handle scenes with reflections. I will then discuss a novel gradient-based technique for image-based rendering that can intrinsically handle scenes with reflections.
Driven by the increasing demand for photorealistic computer-generated images, graphics is currently undergoing a substantial transformation to physics-based approaches which accurately reproduce the interaction of light and matter. Progress on both sides of this transformation -- physical models and simulation techniques -- has been steady but mostly independent from another. When combined, the resulting methods are in many cases impracticably slow and require unrealistic workarounds to process even simple everyday scenes. My research lies at the interface of these two research fields; my goal is to break down the barriers between simulation techniques and the underlying physical models, and to use the resulting insights to develop realistic methods that remain efficient over a wide range of inputs.
I will cover three areas of recent work: the first involves volumetric modeling approaches to create realistic images of woven and knitted cloth. Next, I will discuss reflectance models for glitter/sparkle effects and arbitrarily layered materials that are specially designed to allow for efficient simulations. In the last part of the talk, I will give an overview of Manifold Exploration, a Markov Chain Monte Carlo technique that is able to reason about the geometric structure of light paths in high dimensional configuration spaces defined by the underlying physical models, and which uses this information to compute images more efficiently.
I will present selected research projects of the Photogrammetry and Remote Sensing Group at ETH, including (i) 3D scene flow estimation for stereo video captured from a car; (ii) extraction of road networks from aerial images; and (iii) 3D reconstruction from large, unstructured (e.g. crowd-sourced) image collections.
The growing scale of image and video datasets in vision makes labeling and annotation of such datasets, for training of recognition models, difficult and time consuming. Further, richer models often require richer labelings of the data, that are typically even more difficult to obtain. In this talk I will focus on two models that make use of different forms of supervision for two different vision tasks.
In the first part of this talk I will focus on object detection. The appearance of an object changes profoundly with pose, camera view and interactions of the object with other objects in the scene. This makes it challenging to learn detectors based on an object-level labels (e.g., “car”). We postulate that having a richer set of labelings (at different levels of granularity) for an object, including finer-grained sub-categories, consistent in appearance and view, and higher-order composites – contextual groupings of objects consistent in their spatial layout and appearance, can significantly alleviate these problems. However, obtaining such a rich set of annotations, including annotation of an exponentially growing set of object groupings, is infeasible. To this end, we propose a weakly-supervised framework for object detection where we discover subcategories and the composites automatically with only traditional object-level category labels as input.
In the second part of the talk I will focus on the framework for large scale image set and video summarization. Starting from the intuition that the characteristics of the two media types are different but complementary, we develop a fast and easily-parallelizable approach for creating not only video summaries but also novel structural summaries of events in the form of the storyline graphs. The storyline graphs can illustrate various events or activities associated with the topic in the form of a branching directed network. The video summarization is achieved by diversity ranking on the similarity graphs between images and video frame, thereby treating consumer image as essentially a form of weak-supervision. The reconstruction of storyline graphs on the other hand is formulated as inference of the sparse time-varying directed graphs from a set of photo streams with assistance of consumer videos.
Time permitting I will also talk about a few other recent project highlights.
Abstract: I will present a general framework for modelling and recovering 3D shape and pose using subdivision surfaces. To demonstrate this frameworks generality, I will show how to recover both a personalized rigged hand model from a sequence of depth images and a blend shape model of dolphin pose from a collection of 2D dolphin images. The core requirement is the formulation of a generative model in which the control vertices of a smooth subdivision surface are parameterized (e.g. with joint angles or blend weights) by a differentiable deformation function. The energy function that falls out of measuring the deviation between the surface and the observed data is also differentiable and can be minimized through standard, albeit tricky, gradient based non-linear optimization from a reasonable initial guess. The latter can often be obtained using machine learning methods when manual intervention is undesirable. Satisfyingly, the "tricks" involved in the former are elegant and widen the applicability of these methods.
In order to avoid an expensive manual labeling process or to learn object classes autonomously without human intervention, object discovery techniques have been proposed that extract visual similar objects from weakly labelled videos. However, the problem of discovering small or medium sized objects is largely unexplored. We observe that videos with activities involving human-object interactions can serve as weakly labelled data for such cases. Since neither object appearance nor motion is distinct enough to discover objects in these videos, we propose a framework that samples from a space of algorithms and their parameters to extract sequences of object proposals. Furthermore, we model similarity of objects based on appearance and functionality, which is derived from human and object motion. We show that functionality is an important cue for discovering objects from activities and demonstrate the generality of the model on three challenging RGB-D and RGB datasets.
In this talk I will discuss two related problems in 3D reconstruction: (i) recovering the 3D shape of a temporally varying non-rigid 3D surface given a single video sequence and (ii) reconstructing different instances of the same object class category given a large collection of images from that category. In both cases we extract dense 3D shape information by analysing shape variation -- in one case of the same object instance over time and in the other across different instances of objects that belong to the same class.
First I will discuss the problem of dense capture of 3D non-rigid surfaces from a monocular video sequence. We take a purely model-free approach where no strong assumptions are made about the object we are looking at or the way it deforms. We apply low rank and spatial smoothness priors to obtain dense non-rigid models using a variational approach.
Second I will describe our recent approach to populating the Pascal VOC dataset with dense, per-object 3D reconstructions, bootstrapped from class labels, ground truth figure-ground segmentations and a small set of keypoint annotations. Our proposed algorithm first estimates camera viewpoint using rigid structure-from-motion, then reconstructs objects shapes by optimizing over visual hull proposals guided by loose within-class shape similarity assumptions.
Even though many challenges remain unsolved, in recent years computer graphics algorithms to render photo-realistic imagery have seen tremendous progress. An important prerequisite for high-quality renderings is the availability of good models of the scenes to be rendered, namely models of shape, motion and appearance. Unfortunately, the technology to create such models has not kept pace with the technology to render the imagery. In fact, we observe a content creation bottleneck, as it often takes man months of tedious manual work by a animation artists to craft models of moving virtual scenes.
To overcome this limitation, the research community has been developing techniques to capture models of dynamic scenes from real world examples, for instance methods that rely on footage recorded with cameras or other sensors. One example are performance capture methods that measure detailed dynamic surface models, for example of actors or an actor's face, from multi-view video and without markers in the scene. Even though such 4D capture methods made big strides ahead, they are still at an early stage of their development. Their application is limited to scenes of moderate complexity in controlled environments, reconstructed detail is limited, and captured content cannot be easily modified, to name only a few restrictions.
In this talk, I will elaborate on some ideas on how to go beyond this limited scope of 4D reconstruction, and show some results from our recent work. For instance, I will show how we can capture more complex scenes with many objects or subjects in close interaction, as well as very challenging scenes of a smaller scale, such a hand motion. The talk will also show how we can capitalize on more sophisticated light transport models and inverse rendering to enable high-quality reconstruction in much more uncontrolled scenes, eventually also outdoors, and with very few cameras. I will also demonstrate how to represent captured scenes such that they can be conveniently modified. If time allows, the talk will cover some of our recent ideas on how to perform advanced edits of videos (e.g. removing or modifying dynamic objects in scenes) by exploiting reconstructed 4D models, as well as robustly found inter- and intra-frame correspondences.
Organizers: Gerard Pons-Moll
A goal in virtual reality is for the user to experience a synthetic environment as if it were real. Engagement with virtual actors is a big part of the sensory context, thus getting the people "right" is critical for success. Size, shape, gender, ethnicity, clothing, color, texture, movement, among other attributes must be layered and nuanced to provide an accurate encounter between an actor and a user. In this talk, I discuss the development of digital human models and how they may be improved to obtain the high realism for successful engagement in a virtual world.