Výsledky vyhledávání - "Tsang, Clement"

Report

fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence

Autor: Williams, Francis, Huang, Jiahui, Swartz, Jonathan, Klár, Gergely, Thakkar, Vijay, Cong, Matthew, Ren, Xuanchi, Li, Ruilong, Fuji-Tsang, Clement, Fidler, Sanja, Sifakis, Eftychios, Museth, Ken

We present fVDB, a novel GPU-optimized framework for deep learning on large-scale 3D data. fVDB provides a complete set of differentiable primitives to build deep learning architectures for common tasks in 3D learning such as convolution, pooling, at

Externí odkaz: http://arxiv.org/abs/2407.01781

Zobrazit plný text záznamu

Report

DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer

Autor: Chen, Wenzheng, Litalien, Joey, Gao, Jun, Wang, Zian, Tsang, Clement Fuji, Khamis, Sameh, Litany, Or, Fidler, Sanja

We consider the challenging problem of predicting intrinsic object properties from a single image by exploiting differentiable renderers. Many previous learning-based approaches for inverse graphics adopt rasterization-based renderers and assume naiv

Externí odkaz: http://arxiv.org/abs/2111.00140

Zobrazit plný text záznamu

Report

Learning Deformable Tetrahedral Meshes for 3D Reconstruction

Autor: Gao, Jun, Chen, Wenzheng, Xiang, Tommy, Tsang, Clement Fuji, Jacobson, Alec, McGuire, Morgan, Fidler, Sanja

3D shape representations that accommodate learning-based 3D reconstruction are an open problem in machine learning and computer graphics. Previous work on neural 3D reconstruction demonstrated benefits, but also limitations, of point cloud, voxel, su

Externí odkaz: http://arxiv.org/abs/2011.01437

Zobrazit plný text záznamu

Report

Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Research

Autor: Jatavallabhula, Krishna Murthy, Smith, Edward, Lafleche, Jean-Francois, Tsang, Clement Fuji, Rozantsev, Artem, Chen, Wenzheng, Xiang, Tommy, Lebaredian, Rev, Fidler, Sanja

We present Kaolin, a PyTorch library aiming to accelerate 3D deep learning research. Kaolin provides efficient implementations of differentiable 3D modules for use in deep learning systems. With functionality to load and preprocess several popular 3D

Externí odkaz: http://arxiv.org/abs/1911.05063

Zobrazit plný text záznamu