Following the success of the past three years, Tsinghua University Press will continue to sponsor an annual award for the best paper published in Computational Visual Media. After carefully considering the 30 papers published in 2018, the Editorial Board chose the paper: Photometric stereo for strong specular highlights [1] as the winner of the Best Paper Award, while three other papers: Knowledge graph construction with structure and parameter learning for indoor scene design [2], Robust edge-preserving surface mesh polycube deformation [3], and Transferring pose and augmenting background for deep human image parsing and its applications [4], have won Honorable Mention Awards.

Large-scale deformations of a tubular object, or generalized cylinder, are often defined by a target shape for its center curve, typically using a parametric target curve. This task is non-trivial for free-form deformations or direct manipulation methods because it is hard to manually control the centerline by adjusting control points. Most skeleton-based methods are no better, again due to the small number of manually adjusted control points. In this paper, we propose a method to deform a generalized cylinder based on its skeleton composed of a centerline and orthogonal cross sections. Although we are not the first to use such a skeleton, we propose a novel skeletonization method that tries to minimize the number of intersections between neighboring cross sections by means of a relative curvature condition to detect intersections. The mesh deformation is first defined geometrically by deforming the centerline and mapping the cross sections. Rotation minimizing frames are used during mapping to control twisting. Secondly, given displacements on the cross sections, the deformation is decomposed into finely subdivided regions. We limit distortion at these vertices by minimizing an elastic thin shell bending energy, in linear time. Our method can handle complicated generalized cylinders such as the human colon.

Detecting small objects is a challenging task. We focus on a special case: the detection and classification of traffic signals in street views. We present a novel framework that utilizes a visual attention model to make detection more efficient, without loss of accuracy, and which generalizes. The attention model is designed to generate a small set of candidate regions at a suitable scale so that small targets can be better located and classified. In order to evaluate our method in the context of traffic signal detection, we have built a traffic light benchmark with over 15,000 traffic light instances, based on Tencent street view panoramas. We have tested our method both on the dataset we have built and the Tsinghua–Tencent 100K (TT100K) traffic sign benchmark. Experiments show that our method has superior detection performance and is quicker than the general faster RCNN object detection framework on both datasets. It is competitive with state-of-the-art specialist traffic sign detectors on TT100K, but is an order of magnitude faster. To show generality, we tested it on the LISA dataset without tuning, and obtained an average precision in excess of 90%.

Texture synthesis is widely used for modeling the appearance of virtual objects. However, traditional texture synthesis techniques emphasize creation of optimal target textures, and pay insufficient attention to choice of suitable input texture exemplars. Currently, obtaining texture exemplars from natural images is a labor intensive task for the artists, requiring careful photography and significant postprocessing. In this paper, we present an automatic texture exemplar extraction method based on global and local textureness measures. To improve the efficiency of dominant texture identification, we first perform Poisson disk sampling to randomly and uniformly crop patches from a natural image. For global textureness assessment, we use a GIST descriptor to distinguish textured patches from non-textured patches, in conjunction with SVM prediction. To identify real texture exemplars consisting solely of the dominant texture, we further measure the local textureness of a patch by extracting and matching the local structure (using binary Gabor pattern (BGP)) and dominant color features (using color histograms) between a patch and its sub-regions. Finally, we obtain optimal texture exemplars by scoring and ranking extracted patches using these global and local textureness measures. We evaluate our method on a variety of images with different kinds of textures. A convincing visual comparison with textures manually selected by an artist and a statistical study demonstrate its effectiveness.

We present a new method for editing smoke animations by directly deforming the grid used for simulation. We present a modification to the widely used semi-Lagrangian advection operator and use it to transfer the deformation from the grid to the smoke body. Our modified operator bends the smoke particle streamlines according to the deformation gradient. We demonstrate that the controlled smoke animation preserves the fine-grained vortical velocity components and incompressibility constraints, while conforming to the deformed grid. Moreover, our approach enables interactive 3D smoke animation editing by using a reduced-dimensional subspace. Overall, our method makes it possible to use current mesh editing tools to control the smoke body.

The integration of surface normals for the purpose of computing the shape of a surface in 3D space is a classic problem in computer vision. However, even nowadays it is still a challenging task to devise a method that is flexible enough to work on non-trivial computational domains with high accuracy, robustness, and computational efficiency. By uniting a classic approach for surface normal integration with modern computational techniques, we construct a solver that fulfils these requirements. Building upon the Poisson integration model, we use an iterative Krylov subspace solver as a core step in tackling the task. While such a method can be very efficient, it may only show its full potential when combined with suitable numerical preconditioning and problem-specific initialisation. We perform a thorough numerical study in order to identify an appropriate preconditioner for this purpose. To provide suitable initialisation, we compute this initial state using a recently developed fast marching integrator. Detailed numerical experiments illustrate the benefits of this novel combination. In addition, we show on real-world photometric stereo datasets that the developed numerical framework is flexible enough to tackle modern computer vision applications.

Iris folding is an art-form consisting of layered strips of paper, forming a spiral pattern behind an aperture, which can be used to make cards and gift tags. This paper describes an interactive computational tool to assist in the design and construction of original iris folding patterns. The design of iris folding patterns is formulated as the calculation of a circumscribed polygonal sequence around a seed polygon. While it is possible to compute the positions of vertices analytically for a regular polygon, it is not straightforward to do so for irregular polygons. We give a numerical method for irregular polygons, which can be applied to arbitrary convex seed polygons. The user can quickly experiment with various patterns using the system prior to constructing the art-form.

In the field of cranio-maxillofacial (CMF) surgery, surgical simulation is becoming a very powerful tool to plan surgery and simulate surgical results before actually performing a CMF surgical procedure. Reliable prediction of facial soft tissue changes is in particular essential for better preparation and to shorten the time taken for the operation. This paper presents a surgical simulation system to predict facial soft tissue changes caused by the movement of bone segments during CMF surgery. Two experiments were designed to test the feasibility of this simulation system. The test results demonstrate the feasibility of fast and good prediction of post-operative facial appearance, with texture. Our surgical simulation system is applicable to computer-assisted CMF surgery.

Inferring the functionality of an object from a single RGBD image is difficult for two reasons: lack of semantic information about the object, and missing data due to occlusion. In this paper, we present an interactive framework to recover a 3D functional prototype from a single RGBD image. Instead of precisely reconstructing the object geometry for the prototype, we mainly focus on recovering the object’s functionality along with its geometry. Our system allows users to scribble on the image to create initial rough proxies for the parts. After user annotation of high-level relations between parts, our system automatically jointly optimizes detailed joint parameters (axis and position) and part geometry parameters (size, orientation, and position). Such prototype recovery enables a better understanding of the underlying image geometry and allows for further physically plausible manipulation. We demonstrate our framework on various indoor objects with simple or hybrid functions.