Wenwu Yang

Zhejiang Gongshang University · Computer Science

By leveraging temporal dependency in video sequences , multi-frame human pose estimation algorithms have demonstrated remarkable results in complicated situations , such as occlusion, motion blur, and video defocus. These algorithms are predominantly based on heatmaps, resulting in high computation and storage requirements per frame, which limits t...

p> Immersive cultural performances with virtual-real fusion effects are the future development trend in the exhibition and stage industry. However, current virtual-real stage performances heavily rely on traditional sequential design and arrangements. During the performance, actors must move to specific positions based on the musical beat and execu...

Markerless multi-person 3D motion capture techniques find applications in various domains such as digital film and animation, 3D games, virtual-real interaction, and human gait analysis. However, most research papers tend to focus on algorithm innovation rather than building an effective motion capture system. In this paper, we present a lightweigh...

Different from human vision, which can adapt to various lighting environments, the performance of existing 2D human object detection algorithms will be significantly reduced in the scene of drastic lighting changes. In order to solve this problem, this paper proposes a two-dimensional human object detection method which adapts to the environment of...

Effective expression feature representations generated by a triplet-based deep metric learning are highly advantageous for facial expression recognition (FER). The performance of triplet-based deep metric learning is contingent upon identifying the best threshold for triplet loss. Threshold validation, however, is tough and challenging, as the idea...

Reconstructing a 3D face from a single image is a crucial task in numerous multimedia applications. Face images with ground-truth 3D face shapes are scarce, so unsupervised deep learning methods, which rely primarily on the free supervision signal derived from the visual disparity between the input image and the rendered counterpart of the predicte...

This paper presents a rigidity-preserving morphing technique that blends a pair of 2D shapes in a controllable manner. The morphing is controllable in two aspects: 1) motion dynamics in the interpolation sequences can be effectively enhanced through an intuitive skeleton control and 2) not only the boundaries but also the interior features of the s...

Recent work on anatomical face modeling focuses mainly on facial muscles and their activation. This paper considers a different aspect of anatomical face modeling: kinematic modeling of the jaw, i.e., the temporomandibular joint (TMJ). Previous work often relies on simple models of jaw kinematics, even though the actual physiological behavior of th...

Stroke correspondence construction is a precondition for vectorized 2D animation inbetweening and remains a challenging problem. This paper introduces the FTP‐SC, a fuzzy topology preserving stroke correspondence technique, which is accurate and provides the user more effective control on the correspondence result than previous matching approaches....

This paper considers a different aspect of anatomical face modeling: kinematic modeling of the jaw, i.e., the Temporo-Mandibular Joint (TMJ). Previous work often relies on simple models of jaw kinematics, even though the actual physiological behavior of the TMJ is quite complex, allowing not only for mouth opening, but also for some amount of sidew...

This paper presents a context-aware computer aided inbetweening (CACAI) technique that interpolates planar strokes to generate inbetween frames from a given set of key frames. The inbetweening is context-aware in the sense that not only the stroke’s shape but also the context (i.e., the neighborhood of a stroke) in which a stroke appears are taken...

Deformation method based on moving least squares (MLS) allows the user to manipulate 2D characters using either sets of points or line segments in real time. However, the traditional MLS deformation spreads the deformation of the controls with respect to the spatial distance, but oblivious to the shape topology, which would possibly lead to distort...

Traditional image recognition approaches can achieve high performance only when the images have high resolution and superior quality. A new vehicle logo recognition (VLR) method is proposed to treat low-resolution and poor-quality images captured from urban crossings in intelligent transport system, and the proposed approach is based on statistical...

This paper presents a shape morphing technique that interpolates a pair of 2D polygons or curves. Firstly, a user-guided feature point correspondence is introduced to associate similar parts between the source and target shapes, which allows user to control the correspondence results effectively and flexibly. Secondly, to fully capture the global a...

This paper presents a skeleton-based method for deforming 2D characters. While previous skeleton-based methods drive the shape deformation by binding the skeleton to the shape, our method does so by propagating the skeleton transformations over the shape. In this way, the tedious process of weight selection in previous skeleton-based methods is not...

This paper presents a method that generates natural and intuitive deformations via direct manipulation and smooth interpolation for multi-element 2D shapes. Observing that the structural relationships between different parts of a multi-element 2D shape are important for capturing its feature semantics, we introduce a simple structure called a featu...

2D shape morphing has been widely used in 2D character animation, special effect of film, and geometric modeling etc. Previous algorithms mostly associate similar regions of the input shapes using the shape's geometric entities such as edge, angle, area or skeleton, but do not take into account the visual features of the shapes. This paper presents...

This paper presents a new method which allows user to manipulate a two-dimensional shape in an intutive and flexible way. The shape is discretized as a regular grid. User places handles on the grid and manipulates the shape by moving the handles to the desired positions. To meet the constraints of the users manipulation, the grid is then deformed i...

The paper presents a new method to interpolate a pair of 2D shapes that are represented by piecewise linear curves. The method addresses two key problems in 2D shape morphing process: feature correspondence and path interpolation. First, a robust feature metric is defined to measure the similarity of a pair of 2D shapes in terms of visual appearanc...

The paper presents a 2D or 3D shape deformation method which incorporates global and local stiffness controls. First, a geometric object is embedded into a regular lattice and then the deformation is conducted on the lattice; thus, the method is independent of the underlying object representation. The lattice cells are organized as overlapping loca...

A 2D polygonal shape copy-and-paste method is proposed which is based on a multiple planar shapes blending algorithm. First sub-shapes are specified and selected, which correspond to user-defined visual features on the input shapes. Then they are copied and pasted with contribution weights to generate new shapes via a modified intrinsic 2D shape bl...

2-D polygon shape blending has been widely used in 2 -D character animation, pattern matching, and geometric modeling. Previous algorithms mostly tend to use the polygon's geometric elements such as edge, angle, area and skeleton, to associate the regions on the two shapes which look alike. However they ignore the visual features of two polygonal s...