This paper presents our winning entry for the EVA 2019 data competition, the aim of which is to predict Red Sea surface temperature extremes over space and time. To achieve this, we used a stochastic partial differential equation (Poisson equation) based method, improved through a regularization to penalize large magnitudes of solutions. This approach is shown to be successful according to the competition’s evaluation criterion, i.e. a threshold-weighted continuous ranked probability score. Our stochastic Poisson equation and its boundary conditions resolve the data’s non-stationarity naturally and effectively. Meanwhile, our numerical method is computationally efficient at dealing with the data’s high dimensionality, without any parameter estimation. It demonstrates the usefulness of stochastic differential equations on spatio-temporal predictions, including the extremes of the process.@en

In this paper, we present a new computational pipeline for designing and fabricating 4D garments as knitwear that considers comfort during body movement. This is achieved by careful control of elasticity distribution to reduce uncomfortable pressure and unwanted sliding caused by body motion. We exploit the ability to knit patterns in different elastic levels by single-jersey jacquard (SJJ) with two yarns. We design the distribution of elasticity for a garment by physics-based computation, the optimized elasticity on the garment is then converted into instructions for a digital knitting machine by two algorithms proposed in this paper. Specifically, a graph-based algorithm is proposed to generate knittable stitch meshes that can accurately capture the 3D shape of a garment, and a tiling algorithm is employed to assign SJJ patterns on the stitch mesh to realize the designed distribution of elasticity. The effectiveness of our approach is verified on simulation results and on specimens physically fabricated by knitting machines. @en

Garments, one of the human basic needs, were customized and handmade before the Industrial Revolution. After the realization of mass production, the cost of a piece of clothing became lower, but some disadvantages arose. Garments were no longer made to measure and overproduction caused environmental problems. The new developments in digital garment design and digital customization target addressing these limitations. The computational design of knitting attracted increased attention in recent years. In this dissertation, we consider the customized design and fabrication of 3D and 4D garments as knitwears. The 3D knitwear fits the target human body, and the 4D knitwear also considers comfort during body movement. The main research question (RQ) is: How to design customized 3D and 4D knitwear and generate instructions for a digital knitting machine? In this dissertation, we researched computational knitwear design methods. We considered not only 3D fitting but also comfort during motion (4D). Our research can be applied in garment production (especially mass customization) or other knitting applications. Garment designers and other industrial designers can use the proposed methods to generate knitting instructions for free-form 3D surfaces. Our 4D design method helps designers place elastic or other varied knitting structures while keeping the intended 3D shape. This dissertation presents new perspectives on computational approaches to existing manufacturing techniques. It also provides enough details to further develop such design systems to be applied in practice.@en

In this paper, we propose a method to reconstruct a digital 3D model of a stolen/damaged statue using photogrammetric methods. This task is challenging because the number of available photos for a stolen statue is in general very limited – especially the side/back view photos. Besides using standard structure-from-motion and multi-view stereo methods, we match image pairs with low overlap using sliding windows and maximize the normalized cross-correlation (NCC) based patch-consistency so that the image pairs can be well aligned into a complete model to build the 3D mesh surface. Our method is based on the prior of the planar side on the statue’s pedestal, which can cover a large range of statues. We hope this work will motivate more research efforts for the reconstruction of those stolen/damaged statues and heritage preservation.@en

Monocular image based 3D object retrieval is a novel and challenging research topic in the field of 3D object retrieval. Given a RGB image captured in real world, it aims to search for relevant 3D objects from a dataset. To advance this promising research, we organize this SHREC track and build the first monocular image based 3D object retrieval benchmark by collecting 2D images from ImageNet and 3D objects from popular 3D datasets such as NTU, PSB, ModelNet40 and ShapeNet. The benchmark contains classified 21,000 2D images and 7,690 3D objects of 21 categories. This track attracted 9 groups from 4 countries and the submission of 20 runs. To have a comprehensive comparison, 7 commonly-used retrieval performance metrics have been used to evaluate their retrieval performance. The evaluation results show that the supervised cross domain learning get the superior retrieval performance (Best NN is 97.4 %) by bridging the domain gap with label information. However, there is still a big challenge for unsupervised cross domain learning (Best NN is 61.2%), which is more practical for the real application. Although we provided both view images and OBJ file for each 3D model, all the participants use the view images to represent the 3D model. One of the interesting work in the future is directly using the 3D information and 2D RGB information to solve the task of monocular Image based 3D model retrieval.@en

Monocular image based 3D object retrieval is a novel and challenging research topic in the field of 3D object retrieval. Given a RGB image captured in real world, it aims to search for relevant 3D objects from a dataset. To advance this promising research, we organize this SHREC track and build the first monocular image based 3D object retrieval benchmark by collecting 2D images from ImageNet and 3D objects from popular 3D datasets such as NTU, PSB, ModelNet40 and ShapeNet. The benchmark contains classified 21,000 2D images and 7,690 3D objects of 21 categories. This track attracted 9 groups from 4 countries and the submission of 20 runs. To have a comprehensive comparison, 7 commonly-used retrieval performance metrics have been used to evaluate their retrieval performance. The evaluation results show that the supervised cross domain learning get the superior retrieval performance (Best NN is 97.4 %) by bridging the domain gap with label information. However, there is still a big challenge for unsupervised cross domain learning (Best NN is 61.2%), which is more practical for the real application. Although we provided both view images and OBJ file for each 3D model, all the participants use the view images to represent the 3D model. One of the interesting work in the future is directly using the 3D information and 2D RGB information to solve the task of monocular Image based 3D model retrieval.@en

Monocular image based 3D object retrieval is a novel and challenging research topic in the field of 3D object retrieval. Given a RGB image captured in real world, it aims to search for relevant 3D objects from a dataset. To advance this promising research, we organize this SHREC track and build the first monocular image based 3D object retrieval benchmark by collecting 2D images from ImageNet and 3D objects from popular 3D datasets such as NTU, PSB, ModelNet40 and ShapeNet. The benchmark contains classified 21,000 2D images and 7,690 3D objects of 21 categories. This track attracted 9 groups from 4 countries and the submission of 20 runs. To have a comprehensive comparison, 7 commonly-used retrieval performance metrics have been used to evaluate their retrieval performance. The evaluation results show that the supervised cross domain learning get the superior retrieval performance (Best NN is 97.4 %) by bridging the domain gap with label information. However, there is still a big challenge for unsupervised cross domain learning (Best NN is 61.2%), which is more practical for the real application. Although we provided both view images and OBJ file for each 3D model, all the participants use the view images to represent the 3D model. One of the interesting work in the future is directly using the 3D information and 2D RGB information to solve the task of monocular Image based 3D model retrieval.@en