Browsing by Author "Manocha, Dinesh"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Efficient and Reliable Self‐Collision Culling Using Unprojected Normal Cones(© 2017 The Eurographics Association and John Wiley & Sons Ltd., 2017) Wang, Tongtong; Liu, Zhihua; Tang, Min; Tong, Ruofeng; Manocha, Dinesh; Chen, Min and Zhang, Hao (Richard)We present an efficient and accurate algorithm for self‐collision detection in deformable models. Our approach can perform discrete and continuous collision queries on triangulated meshes. We present a simple and linear time algorithm to perform the normal cone test using the unprojected 3D vertices, which reduces to a sequence point‐plane classification tests. Moreover, we present a hierarchical traversal scheme that can significantly reduce the number of normal cone tests and the memory overhead using front‐based normal cone culling. The overall algorithm can reliably detect all (self) collisions in models composed of hundreds of thousands of triangles. We observe considerable performance improvement over prior continuous collision detection algorithms.We present an efficient and accurate algorithm for self‐collision detection in deformable models. Our approach can perform discrete and continuous collision queries on triangulated meshes. We present a simple and linear time algorithm to perform the normal cone test using the unprojected 3D vertices, which reduces to a sequence point‐plane classification tests. Moreover, we present a hierarchical traversal scheme that can significantly reduce the number of normal cone tests and the memory overhead using front‐based normal cone culling. The overall algorithm can reliably detect all (self) collisions in models composed of hundreds of thousands of triangles. We observe considerable performance improvement over prior continuous collision detection algorithms.Item GPU-Based Contact-Aware Trajectory Optimization Using A Smooth Force Model(ACM, 2019) Pan, Zherong; Ren, Bo; Manocha, Dinesh; Batty, Christopher and Huang, JinWe present a new formulation of trajectory optimization for articulated bodies. Our approach uses a fully differentiable dynamic model of the articulated body, and a smooth force model that approximates all kinds of internal/external forces as a smooth function of the articulated body's kinematic state. Our formulation is contact-aware and its complexity is not dependent on the contact positions or the number of contacts. Furthermore, we exploit the block-tridiagonal structure of the Hessian matrix and present a highly parallel Newton-type trajectory optimizer that maps well to GPU architectures. Moreover, we use a Markovian regularization term to overcome the local minima problems in the optimization formulation. We highlight the performance of our approach using a set of locomotion tasks performed by characters with 15 − 35 DOFs. In practice, our GPU-based algorithm running on a NVIDIA TITAN-X GPU provides more than 30× speedup over a multi-core CPU-based implementation running on Intel Xeon E5-1620 CPU. In addition, we demonstrate applications of our method on various applications such as contact-rich motion planning, receding-horizon control, and motion graph construction.Item HMLFC: Hierarchical Motion-Compensated Light Field Compression for Interactive Rendering(The Eurographics Association and John Wiley & Sons Ltd., 2019) Pratapa, Srihari; Manocha, Dinesh; Steinberger, Markus and Foley, TimWe present a new motion-compensated hierarchical compression scheme (HMLFC) for encoding light field images (LFI) that is suitable for interactive rendering. Our method combines two different approaches, motion compensation schemes and hierarchical compression methods, to exploit redundancies in LFI. The motion compensation schemes capture the redundancies in local regions of the LFI efficiently (local coherence) and the hierarchical schemes capture the redundancies present across the entire LFI (global coherence). Our hybrid approach combines the two schemes effectively capturing both local as well as global coherence to improve the overall compression rate. We compute a tree from LFI using a hierarchical scheme and use phase shifted motion compensation techniques at each level of the hierarchy. Our representation provides random access to the pixel values of the light field, which makes it suitable for interactive rendering applications using a small run-time memory footprint. Our approach is GPU friendly and allows parallel decoding of LF pixel values. We highlight the performance on the two-plane parameterized light fields and obtain a compression ratio of 30-800x with a PSNR of 40-45 dB. Overall, we observe a 2-5x improvement in compression rates using HMLFC over prior light field compression schemes that provide random access capability. In practice, our algorithm can render new views of resolution 512x512 on an NVIDIA GTX-980 at around 200 fps.Item LPaintB: Learning to Paint from Self-Supervision(The Eurographics Association, 2019) Jia, Biao; Brandt, Jonathan; Mech, Radomír; Kim, Byungmoon; Manocha, Dinesh; Lee, Jehee and Theobalt, Christian and Wetzstein, GordonWe present a novel reinforcement learning-based natural media painting algorithm. Our goal is to reproduce a reference image using brush strokes and we encode the objective through observations. Our formulation takes into account that the distribution of the reward in the action space is sparse and training a reinforcement learning algorithm from scratch can be difficult. We present an approach that combines self-supervised learning and reinforcement learning to effectively transfer negative samples into positive ones and change the reward distribution. We demonstrate the benefits of our painting agent to reproduce reference images with brush strokes. The training phase takes about one hour and the runtime algorithm takes about 30 seconds on a GTX1080 GPU reproducing a 1000x800 image with 20,000 strokes.Item N-Cloth: Predicting 3D Cloth Deformation with Mesh-Based Networks(The Eurographics Association and John Wiley & Sons Ltd., 2022) Li, Yu Di; Tang, Min; Yang, Yun; Huang, Zi; Tong, Ruo Feng; Yang, Shuang Cai; Li, Yao; Manocha, Dinesh; Chaine, Raphaëlle; Kim, Min H.We present a novel mesh-based learning approach (N-Cloth) for plausible 3D cloth deformation prediction. Our approach is general and can handle cloth or obstacles represented by triangle meshes with arbitrary topologies.We use graph convolution to transform the cloth and object meshes into a latent space to reduce the non-linearity in the mesh space. Our network can predict the target 3D cloth mesh deformation based on the initial state of the cloth mesh template and the target obstacle mesh. Our approach can handle complex cloth meshes with up to 100K triangles and scenes with various objects corresponding to SMPL humans, non-SMPL humans or rigid bodies. In practice, our approach can be used to generate plausible cloth simulation at 30??45 fps on an NVIDIA GeForce RTX 3090 GPU. We highlight its benefits over prior learning-based methods and physicallybased cloth simulators.