4 results
Search Results
Now showing 1 - 4 of 4
Item Computing Surface PolyCube-Maps by Constrained Voxelization(The Eurographics Association and John Wiley & Sons Ltd., 2019) Yang, Yang; Fu, Xiao-Ming; Liu, Ligang; Lee, Jehee and Theobalt, Christian and Wetzstein, GordonWe present a novel method to compute bijective PolyCube-maps with low isometric distortion. Given a surface and its preaxis- aligned shape that is not an exact PolyCube shape, the algorithm contains two steps: (i) construct a PolyCube shape to approximate the pre-axis-aligned shape; and (ii) generate a bijective, low isometric distortion mapping between the constructed PolyCube shape and the input surface. The PolyCube construction is formulated as a constrained optimization problem, where the objective is the number of corners in the constructed PolyCube, and the constraint is to bound the approximation error between the constructed PolyCube and the input pre-axis-aligned shape while ensuring topological validity. A novel erasing-and-filling solver is proposed to solve this challenging problem. Centeral to the algorithm for computing bijective PolyCube-maps is a quad mesh optimization process that projects the constructed PolyCube onto the input surface with high-quality quads. We demonstrate the efficacy of our algorithm on a data set containing 300 closed meshes. Compared to state-of-the-art methods, our method achieves higher practical robustness and lower mapping distortion.Item Deep Video-Based Performance Synthesis from Sparse Multi-View Capture(The Eurographics Association and John Wiley & Sons Ltd., 2019) Chen, Mingjia; Wang, Changbo; Liu, Ligang; Lee, Jehee and Theobalt, Christian and Wetzstein, GordonWe present a deep learning based technique that enables novel-view videos of human performances to be synthesized from sparse multi-view captures. While performance capturing from a sparse set of videos has received significant attention, there has been relatively less progress which is about non-rigid objects (e.g., human bodies). The rich articulation modes of human body make it rather challenging to synthesize and interpolate the model well. To address this problem, we propose a novel deep learning based framework that directly predicts novel-view videos of human performances without explicit 3D reconstruction. Our method is a composition of two steps: novel-view prediction and detail enhancement. We first learn a novel deep generative query network for view prediction. We synthesize novel-view performances from a sparse set of just five or less camera videos. Then, we use a new generative adversarial network to enhance fine-scale details of the first step results. This opens up the possibility of high-quality low-cost video-based performance synthesis, which is gaining popularity for VA and AR applications. We demonstrate a variety of promising results, where our method is able to synthesis more robust and accurate performances than existing state-of-the-art approaches when only sparse views are available.Item Practical Foldover-Free Volumetric Mapping Construction(The Eurographics Association and John Wiley & Sons Ltd., 2019) Su, Jian-Ping; Fu, Xiao-Ming; Liu, Ligang; Lee, Jehee and Theobalt, Christian and Wetzstein, GordonIn this paper, we present a practically robust method for computing foldover-free volumetric mappings with hard linear constraints. Central to this approach is a projection algorithm that monotonically and efficiently decreases the distance from the mapping to the bounded conformal distortion mapping space. After projection, the conformal distortion of the updated mapping tends to be below the given bound, thereby significantly reducing foldovers. Since it is non-trivial to define an optimal bound, we introduce a practical conformal distortion bound generation scheme to facilitate subsequent projections. By iteratively generating conformal distortion bounds and trying to project mappings into bounded conformal distortion spaces monotonically, our algorithm achieves high-quality foldover-free volumetric mappings with strong practical robustness and high efficiency. Compared with existing methods, our method computes mesh-based and meshless volumetric mappings with no prescribed conformal distortion bounds. We demonstrate the efficacy and efficiency of our method through a variety of geometric processing tasks.Item Computational Design of Steady 3D Dissection Puzzles(The Eurographics Association and John Wiley & Sons Ltd., 2019) Tang, Keke; Song, Peng; Wang, Xiaofei; Deng, Bailin; Fu, Chi-Wing; Liu, Ligang; Alliez, Pierre and Pellacini, FabioDissection puzzles require assembling a common set of pieces into multiple distinct forms. Existing works focus on creating 2D dissection puzzles that form primitive or naturalistic shapes. Unlike 2D dissection puzzles that could be supported on a tabletop surface, 3D dissection puzzles are preferable to be steady by themselves for each assembly form. In this work, we aim at computationally designing steady 3D dissection puzzles. We address this challenging problem with three key contributions. First, we take two voxelized shapes as inputs and dissect them into a common set of puzzle pieces, during which we allow slightly modifying the input shapes, preferably on their internal volume, to preserve the external appearance. Second, we formulate a formal model of generalized interlocking for connecting pieces into a steady assembly using both their geometric arrangements and friction. Third, we modify the geometry of each dissected puzzle piece based on the formal model such that each assembly form is steady accordingly. We demonstrate the effectiveness of our approach on a wide variety of shapes, compare it with the state-of-the-art on 2D and 3D examples, and fabricate some of our designed puzzles to validate their steadiness.