SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC On-Demand

AI and DL Research
Presentation
Media
Point Cloud Deep Learning
This presentation shows in-depth comparisons of several neural network models for 3D object classification. Object classification from 2D image is studied thoroughly and widely adopted during last few years by following the advances of deep neural networks. From then, 3D object classification methods are actively studied, and yet not completely mature. Point cloud is most basic format of 3D objects. In this work, we present many neural network models that can be learned from 3D point cloud. It includes directly learning from 3D point cloud, projected 2D pixels, and voxelated volumes. This work uses Princeton ModelNet datasets and ShapeNetCore.v2 dataset, and then provides the comparisons of those neural network models.
This presentation shows in-depth comparisons of several neural network models for 3D object classification. Object classification from 2D image is studied thoroughly and widely adopted during last few years by following the advances of deep neural networks. From then, 3D object classification methods are actively studied, and yet not completely mature. Point cloud is most basic format of 3D objects. In this work, we present many neural network models that can be learned from 3D point cloud. It includes directly learning from 3D point cloud, projected 2D pixels, and voxelated volumes. This work uses Princeton ModelNet datasets and ShapeNetCore.v2 dataset, and then provides the comparisons of those neural network models.  Back
 
Keywords:
AI and DL Research, Graphics and AI, Rendering and Ray Tracing, Real-Time Graphics, GTC Silicon Valley 2018 - ID S8453
Streaming:
Download:
Share:
Graphics Performance Optimization
Presentation
Media
Sketching 3D Animations using CUDA
We present a sketch-based 3D animation application that can easily search and create 3D animation from motion captured database. By using CUDA, The 6.5 hours of motion sequences can be found in few seconds based on users' sketches. And the new motions can be created by connecting the found motion sequences.
We present a sketch-based 3D animation application that can easily search and create 3D animation from motion captured database. By using CUDA, The 6.5 hours of motion sequences can be found in few seconds based on users' sketches. And the new motions can be created by connecting the found motion sequences.  Back
 
Keywords:
Graphics Performance Optimization, Developer - Tools & Libraries, GTC Silicon Valley 2013 - ID P3156
Download:
Share:
Media and Entertainment
Presentation
Media
Motion Retiming using CUDA and Smooth Surfaces
Motion retiming is used to edit character animations to match a given time. It is a non-trivial task to retime the motion of a set of joints since spatio-temporal correlation exists among them. We present a novel approach to motion retiming that exploits the proximity of joints as a way of preserving the motion coherence. Our framework that allows users to intuitively and interactively retime motion using CUDA.
Motion retiming is used to edit character animations to match a given time. It is a non-trivial task to retime the motion of a set of joints since spatio-temporal correlation exists among them. We present a novel approach to motion retiming that exploits the proximity of joints as a way of preserving the motion coherence. Our framework that allows users to intuitively and interactively retime motion using CUDA.  Back
 
Keywords:
Media and Entertainment, Developer - Performance Optimization, GTC Silicon Valley 2015 - ID P5110
Download:
Share:
Rendering and Ray Tracing
Presentation
Media
Sparse Volumetric Representation of Time-Lapse Point Cloud

This talk presents sparse voxelization of time-lapse point cloud. Point cloud has several advantages including capturing easiness, data simplicity, and most fundamental 3D primitive. Because of these advantages, the easy way to collect time-lapse 3D information is by capturing point cloud using laser scan or photogrammetry. However, point cloud representation is lack of spatial connectivity and has notoriously big size of captured data. Our sparse volumetric representation fills the gap between the pros and cons of point cloud by keeping the simplicity and easiness and providing spatial connectivity as well as GPU-friendly data structure. In this talk, we show our massive-scale time-lapse point cloud dataset, the compression as sparse voxels, and further processing in parallel and visualization using GVDB in CUDA.

This talk presents sparse voxelization of time-lapse point cloud. Point cloud has several advantages including capturing easiness, data simplicity, and most fundamental 3D primitive. Because of these advantages, the easy way to collect time-lapse 3D information is by capturing point cloud using laser scan or photogrammetry. However, point cloud representation is lack of spatial connectivity and has notoriously big size of captured data. Our sparse volumetric representation fills the gap between the pros and cons of point cloud by keeping the simplicity and easiness and providing spatial connectivity as well as GPU-friendly data structure. In this talk, we show our massive-scale time-lapse point cloud dataset, the compression as sparse voxels, and further processing in parallel and visualization using GVDB in CUDA.

  Back
 
Keywords:
Rendering and Ray Tracing, Large Scale and Multi-Display Visualization, Real-Time Graphics, GTC Silicon Valley 2017 - ID S7108
Download:
Share:
Virtual Reality and Augmented Reality
Presentation
Media
Massive Time-lapse Point Cloud Rendering with VR
We present our novel methods for visualizing massive scale time-lapse point cloud data, and navigating and handling point cloud VR. Our method provides new approaches for normal and stereoscopic rendering of 120 GB time-lapse point cloud data, and targeted to apply our method to 2 TB data. Time-lapse point cloud has many problems including color mismatching, registration, out-of-core design, and memory management. We generate progressive blue-noise point cloud, and apply sparse buffer extension in OpenGL 4.5, by them, reduce the complexity of out-of-core design and memory manipulation cost. In addition, point cloud with VR is an emerging field so that not many methods are applicable yet. We are investigating a new method that is able to visualize and navigate large point cloud data.
We present our novel methods for visualizing massive scale time-lapse point cloud data, and navigating and handling point cloud VR. Our method provides new approaches for normal and stereoscopic rendering of 120 GB time-lapse point cloud data, and targeted to apply our method to 2 TB data. Time-lapse point cloud has many problems including color mismatching, registration, out-of-core design, and memory management. We generate progressive blue-noise point cloud, and apply sparse buffer extension in OpenGL 4.5, by them, reduce the complexity of out-of-core design and memory manipulation cost. In addition, point cloud with VR is an emerging field so that not many methods are applicable yet. We are investigating a new method that is able to visualize and navigate large point cloud data.  Back
 
Keywords:
Virtual Reality and Augmented Reality, Product & Building Design, In-Situ and Scientific Visualization, GTC Silicon Valley 2016 - ID S6512
Streaming:
Download:
Share: