Yijing Chen, Chuhua Xian, Shuo Jin, Guiqing Li, "3D Shape-adapted Garment Generation with Sketches", Computer Graphics International, September 6-10, 2021, Genever, Switzerland, accepted.

Abstract
Garment generation or reconstruction is becoming extremely demanding for many digital applications, and the traditional process is time-consuming. In recent years, garment reconstruction from sketch leveraging deep learning and principal component analysis (PCA) has made great progress. In this paper, we present a data-driven approach wherein 3D garments are directly generated from sketches combining given body shape parameters. Our framework is an encoder-decoder architecture. In our network, sketch features extracted by DenseNet and body shape parameters were encoded to latent code respectively. Then, the new latent code obtained by adding two latent codes of the sketch and human body shape is decoded by a fully convolutional mesh decoder. Our network enables the body shape adapted detailed 3D garment generation by leveraging garment sketch and body shape parameters. With the fully convolutional mesh decoder, the network can show the effect of body shape and sketch on the generated garment. Experimental results show that the fully convolutional mesh decoder we used to reconstruct the garment performs higher accuracy and maintains lots of detail compared with the PCA-based method.

Xin Liu, Chuhua Xian, Shuo Jin, Guiqing Li, "Surface attributes driven volume segmentation for 3D-printing", Special Issue of Computational Fabrication, Computers & Graphics, Volume 100, Pages 43-53, November 2021.

Abstract
Volume segmentation based on surface attributes is an essential problem in multi-material fabrication and model packing. In practice, current mainstream fabrication techniques have difficulties in yielding models with diverse surface attributes in one pass owing to their craft limitations, making model segmentation a sensible choice for model realization. Partitioning 3D objects into single-attribute volumetric parts prevents fabricating models with different material in a single printing procedure, whereas the arisen challenge is to determine a reliable segmentation solution that is able to handle complicated models in various use scenarios. To achieve this goal, we propose a novel volume partition algorithm generating feasible volumetric parts, each of which is affiliated with one single surface attribute. Our technique enables model segmentation with least conflict and constrained wall thickness so that each volumetric segment can be realized independently by 3D-printing. Generally, it starts with computing a partition proposal guided by radial-based-function iso-surface, then optimizes segmentation interface with a prescribed minimal printing thickness to produce high-quality surface for every volumetric part, and finally splits unextractable volumetric parts into smaller sub-volumes to ensure assemblability of the whole model. As previous methods do not work well in optimizing segment interface for printing, we propose a differential evolution based smoothing algorithm to generate smooth and continuous interface, declining the risk of collision between adjacent volumetric parts. Extensive experimental results are provided in this paper to demonstrate the effectiveness and quality of our proposed technique, showing its advantages on model manufacture over prior methods.

Zhiguang Pan, Chuhua Xian, Shuo Jin, Guiqing Li, "Progressive Furniture Model Decimation with Texture Preservation", Journal of Computer Science and Technology 34(6): 1258–1268 Nov. 2019.

Abstract
In digital furniture design, skillful designers usually use professional software to create new furniture designs with various textures and then take advantage of rendering tools to produce eye-catching design results. Generally, a fine-grained furniture model holds many geometric details, inducing significant time cost to model rendering and large data size for storage that are not desired in application scenarios where efficiency is greatly emphasized. To accelerate the rendering process while keeping good rendering results as many as possible, we develop a novel decimation technique which not only reduces the number of faces on furniture models, but also retains their geometric and texture features. Two metrics are utilized in our approach to measure the distortion of texture features. Considering these two metrics as guidance for decimation, high texture distortion can be avoided in simplifying the geometric models. Therefore, we are able to build multi-level representations with different detail levels based on the initial design. Our experimental results show that the developed technique can achieve excellent visual effects on the decimated furniture model.

Chuhua Xian, Junxian Huang, Shuo Jin, Guoliang Luo, Charlie C.L. Wang, "Real-time C^2-Weighting Based Character Skinning Powered by GPU", short paper, Proceeding of the Conference on Computer Animation and Social Agents 2017, pp. 11 - 14, Seoul, South Korea, May 2017.

Abstract
Handle driven character skinning is widely favored in animation applications due to its advantages of intuitiveness, effectiveness and simplicity. A research thread to realize this is to compute a proper weighting distribution on points associated with specified handles like points, bars or skeleton, which is critical to the quality of manipulation and can be utilized to produce animation by controlling user handles. In this work, we introduce a new skinning method that is compatible with different model representations, with a key idea of evaluating the local influence of each handle by decomposing the shape domain into small overlapped regions. Thanks to its well-designed formulation, the computation of weights and update of models can be conducted in parallel on GPU, leading to high efficiency and good visual quality supported by the provided experimental and statistical results in this paper.

Shuo Jin, Chengkai Dai, Yang Liu, Charlie C.L. Wang, "Motion Imitation Based on Sparsely Sampled Correspondence", ASME Journal of Computing and Information Science in Engineering, Vol.17, No.4, 041009 (7 pages), June 2017.

Abstract
Existing techniques for motion imitation often suffer a certain level of latency due to their computational overhead or a large set of correspondence samples to search. To achieve real-time imitation with small latency, we present a framework in this paper to reconstruct motion on humanoids based on sparsely sampled correspondence. The imitation problem is formulated as finding the projection of a point from the configuration space of a human’s poses into the configuration space of a humanoid. An optimal projection is defined as the one that minimizes a back-projected deviation among a group of candidates, which can be determined in a very efficient way. Benefited from this formulation, effective projections can be obtained by using sparsely sampled correspondence, whose generation scheme is also introduced in this paper. Our method is evaluated by applying the human’s motion captured by a RGB-D sensor to a humanoid in real time. Continuous motion can be realized and used in the example application of tele-operation.

Chuhua Xian*, Shuo Jin*, Charlie C.L. Wang, "Efficient C^2-Weighting for Image Warping", IEEE Computer Graphics and Applications, IEEE Computer Graphics and Applications, vol. 38, no. 1, pp. 59-76, 2018. (*Joint first authors)

Abstract
Handle-driven image warping based on linear blending is widely used in many applications because of its merits on intuitiveness, efficiency and easiness of implementation. In this paper, we develop a method to compute high-quality weights within a closed domain for image warping. The property of C^2-continuity in weights is guaranteed by the carefully formulated basis functions. The efficiency of our algorithm is ensured by a closed-form formulation of the computation for weights. The cost of inserting a new handle is only the time to evaluate the distances from the new handle to all other sample points in the domain. A virtual handle insertion algorithm is developed to allow users to freely place handles within the domain while preserving the satisfaction of all expected criteria on weights for linear blending. Experimental examples for real-time applications are shown to demonstrate the effectiveness of this method.

Camille Schreck, Damien Rohmer, Stefanie Hahmann, Marie-Paule Cani, Shuo Jin, Charlie C.L. Wang, and Jean-Francis Bloch, "Non-smooth Developable Geometry for Interactively Animating Paper Crumpling", ACM Transactions on Graphics, Vol. 35, No. 1, Article No. 10, December 2015.

Abstract
We present the first method to animate sheets of paper at interactive rates, while automatically generating a plausible set of sharp features when the sheet is crumpled. The key idea is to interleave standard physically-based simulation steps with procedural generation of a piecewise continuous developable surface. The resulting hybrid surface model captures new singular points dynamically appearing during the crumpling process, mimicking the effect of paper fiber fracture. Although the model evolves over time to take these irreversible damages into account, the mesh used for simulation is kept coarse throughout the animation, leading to efficient computations. Meanwhile, the geometric layer ensures that the surface stays almost isometric to its original 2D pattern. We validate our model through measurements and visual comparison with real paper manipulation, and show results on a variety of crumpled paper configurations.

Kailun Hu, Shuo Jin and Charlie C.L. Wang, "Support Slimming for Single Material Based Additive Manufacturing", Computer-Aided Design, Vol. 65, pp. 1 - 10, August 2015.

Abstract
In layer-based additive manufacturing (AM), supporting structures need to be inserted to support the overhanging regions. The adding of supporting structures slows down the speed of fabrication and introduces artifacts onto the finished surface. We present an orientation-driven shape optimizer to slim down the supporting structures used in single material-based AM. The optimizer can be employed as a tool to help designers to optimize the original model to achieve a more self-supported shape, which can be used as a reference for their further design. The model to be optimized is first enclosed in a volumetric mesh, which is employed as the domain of computation. The optimizer is driven by the operations of reorientation taken on tetrahedra with "facing-down" surface facets. We formulate the demand on minimizing shape variation as global rigidity energy. The local optimization problem for determining a minimal rotation is analyzed on the Gauss sphere, which leads to a closed-form solution. Moreover, we also extend our approach to create the functions of controlling the deformation and searching for optimal printing directions.

Shuo Jin, Yunbo Zhang, and Charlie C.L. Wang, "Deformation with Enforced Metrics on Length, Area and Volume", Computer Graphics Forum, Special Issue of Eurographics 2014, April 7 - 11, 2014, Strasbourg, France, Vol. 33, No. 2, pp. 429 - 438, April 2014.

Abstract
Techniques have been developed to deform a mesh with multiple types of constraints. One limitation of prior methods is that the accuracy of demanded metrics on the resultant model cannot be guaranteed. Adding metrics directly as hard constraints to an optimization functional often leads to unexpected distortion when target metrics differ significantly from what are on the input model. In this paper, we present an effective framework to deform mesh models by enforcing demanded metrics on length, area and volume. To approach target metrics stably and minimize distortion, an iterative scale-driven deformation is investigated, and a global optimization functional is exploited to balance the scaling effect at different parts of a model. Examples demonstrate that our approach provides a user-friendly tool for designers who are used to semantic input.