There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Data Mining Practical Machine Learning Tools and Techniques

In this paper, a new technique for modeling textured 3D faces is introduced. 3D faces can either be generated automatically from one or more photographs, or modeled directly through an intuitive user interface. Users are assisted in two key problems of computer aided face modeling. First, new face images or new 3D face models can be registered automatically by computing dense one-to-one correspondence to an internal face model. Second, the approach regulates the naturalness of modeled faces avoiding faces with an “unlikely” appearance. Starting from an example set of 3D face models, we derive a morphable face model by transforming the shape and texture of the examples into a vector space representation. New faces and expressions can be modeled by forming linear combinations of the prototypes. Shape and texture constraints derived from the statistics of our example faces are used to guide manual modeling or automated matching algorithms. We show 3D face reconstructions from single images and their applications for photo-realistic image manipulations. We also demonstrate face manipulations according to complex parameters such as gender, fullness of a face or its distinctiveness.

/pdf/a-morphable-model-for-the-synthesis-of-3d-faces-1fz06uy6kp.pdf

A morphable model for the synthesis of 3D faces

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Emotion and Adaptation

The availability of user check-in data in large volume from the rapid growing location based social networks (LBSNs) enables many important location-aware services to users. Point-of-interest (POI) recommendation is one of such services, which is to recommend places where users have not visited before. Several techniques have been recently proposed for the recommendation service. However, no existing work has considered the temporal information for POI recommendations in LBSNs. We believe that time plays an important role in POI recommendations because most users tend to visit different places at different time in a day, \eg visiting a restaurant at noon and visiting a bar at night. In this paper, we define a new problem, namely, the time-aware POI recommendation, to recommend POIs for a given user at a specified time in a day. To solve the problem, we develop a collaborative recommendation model that is able to incorporate temporal information. Moreover, based on the observation that users tend to visit nearby POIs, we further enhance the recommendation model by considering geographical information. Our experimental results on two real-world datasets show that the proposed approach outperforms the state-of-the-art POI recommendation methods substantially.

/pdf/time-aware-point-of-interest-recommendation-1v6rz29ngs.pdf

Time-aware point-of-interest recommendation

We are presenting techniques for simulating the motion and the deformation of cloth, fabrics or, more generally, deformable surfaces. Our main goal is to be able to simulate any kind of surface without imposing restrictions on shape or geometrical environment. In particular, we are considering difficult situations with respect to deformations and collisions, like wrinkled fabric falling on the ground. Thus, we have enhanced existing algorithms in order to cope with any possible situation. A mechanical model has been implemented to deal with any irregular triangular meshes, handle high deformations despite rough discretisation, and cope with complex interacting collisions. Thus, it should deal efficiently with situations where nonlinearities and discontinuities are really non marginal. Collision detection has also been improved to efficiently detect self-collisions, and also to correctly consider collision orientations despite the lack of surface orientation information from preset geometrical contexts, using consistency checking and correction. We illustrate these features through simulation examples.

/pdf/versatile-and-efficient-techniques-for-simulating-cloth-and-2nkld9qcqw.pdf

Versatile and efficient techniques for simulating cloth and other deformable objects

Despite great progress in 3D pose estimation from single-view images or videos, it remains a challenging task due to the substantial depth ambiguity and severe self-occlusions. Motivated by the effectiveness of incorporating spatial dependencies and temporal consistencies to alleviate these issues, we propose a novel graph-based method to tackle the problem of 3D human body and 3D hand pose estimation from a short sequence of 2D joint detections. Particularly, domain knowledge about the human hand (body) configurations is explicitly incorporated into the graph convolutional operations to meet the specific demand of the 3D pose estimation. Furthermore, we introduce a local-to-global network architecture, which is capable of learning multi-scale features for the graph-based representations. We evaluate the proposed method on challenging benchmark datasets for both 3D hand pose estimation and 3D body pose estimation. Experimental results show that our method achieves state-of-the-art performance on both tasks.

/pdf/exploiting-spatial-temporal-relationships-for-3d-pose-23siuxu3bq.pdf

Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

This paper describes interactive facilities for simulating abstract muscle actions using rational free form deformations (RFFD). The particular muscle action is simulated as the displacement of the control points of the control-unit for an RFFD defined on a region of interest. One or several simulated muscle actions constitute a minimum perceptible action (MPA), which is defined as the atomic action unit, similar to action unit (AU) of the facial action coding system (FACS), to build an expression

Simulation of Facial Muscle Actions Based on Rational Free Form Deformations

Discusses the use of physics-based models for animating clothes on synthetic actors in motion. In this approach, cloth pieces are first designed with polygonal panels in two dimensions, and are then seamed and attached to the actor's body in three dimensions. After the clothes are created, physical properties are simulated and then clothes are animated according to the actor's motion in a physical environment. The paper describes the physical models used and then addresses several problems encountered. It examines how to constrain the elements of deformable objects which are either seamed together or attached to rigid moving objects. It also describes a new approach to the problem of handling collisions among the cloth elements themselves, or between a cloth element and a rigid object like the human body. Finally, the paper discusses how to reduce the number of parameters for improving the interface between the animator and the physics-based model

Nadia Magnenat Thalmann

Papers

Time-aware point-of-interest recommendation

Versatile and efficient techniques for simulating cloth and other deformable objects

Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks

Simulation of Facial Muscle Actions Based on Rational Free Form Deformations

Dressing animated synthetic actors with complex deformable clothes