SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC On-Demand

Presentation
Media
Abstract:
NVIDIA's Turing GPUs contain a brand new hardware accelerator for optical flow. This hardware accelerator, which is independent of CUDA cores, calculates optical flow vectors between a given frame pair at very high accuracy and high performance. This session provides a brief overview of the optical flow functionality and SDK, which was recently released by NVIDIA. We will provide a technical overview of the optical flow engine capabilities, performance and quality benchmarks and results of typical end-to-end use-cases.
NVIDIA's Turing GPUs contain a brand new hardware accelerator for optical flow. This hardware accelerator, which is independent of CUDA cores, calculates optical flow vectors between a given frame pair at very high accuracy and high performance. This session provides a brief overview of the optical flow functionality and SDK, which was recently released by NVIDIA. We will provide a technical overview of the optical flow engine capabilities, performance and quality benchmarks and results of typical end-to-end use-cases.  Back
 
Topics:
Virtual Reality and Augmented Reality, Video and Image Processing
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S91024
Streaming:
Download:
Share:
 
Abstract:
This talk will focus on latest updates of NVIDIA video technologies such as video encoding, decoding and optical flow SDK, with particular emphasis on quality, performance and functionality improvements brought by Turing architecture. We will also discuss applications of the video technologies into various DL/AI use cases and optimization techniques in such use cases. A new release of the video SDK (9.0) and the first version of Optical Flow SDK (1.0) are set to launch in Q1 2019, so this session will be an ideal preview.
This talk will focus on latest updates of NVIDIA video technologies such as video encoding, decoding and optical flow SDK, with particular emphasis on quality, performance and functionality improvements brought by Turing architecture. We will also discuss applications of the video technologies into various DL/AI use cases and optimization techniques in such use cases. A new release of the video SDK (9.0) and the first version of Optical Flow SDK (1.0) are set to launch in Q1 2019, so this session will be an ideal preview.  Back
 
Topics:
Video and Image Processing, Intelligent Video Analytics
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9331
Streaming:
Download:
Share:
 
Abstract:
NVIDIA's video SDK is a set of APIs for hardware-accelerated video encoding and decoding using NVIDIA GPUs. We'll provide an overview of the APIs, with particular emphasis on the latest features, such as FFmpeg support of NVIDIA-accelerated transcoding, quality and performance enhancements. We'll discuss some strategies on efficient usage of GPU video hardware acceleration for use cases such as video inferencing, transcoding, and media archiving.
NVIDIA's video SDK is a set of APIs for hardware-accelerated video encoding and decoding using NVIDIA GPUs. We'll provide an overview of the APIs, with particular emphasis on the latest features, such as FFmpeg support of NVIDIA-accelerated transcoding, quality and performance enhancements. We'll discuss some strategies on efficient usage of GPU video hardware acceleration for use cases such as video inferencing, transcoding, and media archiving.  Back
 
Topics:
AI Application Deployment and Inference, Video and Image Processing
Type:
Talk
Event:
GTC Silicon Valley
Year:
2018
Session ID:
S8601
Streaming:
Download:
Share:
 
Abstract:

We'll provide an overview, updates, and roadmap for various NVIDIA video technologies. These include video SDK for encode and decode, and capture SDK for screen capture and application capture. NVIDIA's video SDK is a set of APIs for hardware-accelerated video encoding and decoding using NVIDIA GPUs. We'll provide an overview of the APIs, with particular emphasis on the latest features, such as FFMPEG/libAV support of NVIDIA-accelerated transcoding, motion-estimation API enhancements, quality and performance enhancements, and new codec support. Capture SDK is a set of APIs provided by NVIDIA for fast capture of the desktop screen or application buffer content. We'll provide an overview of the latest additions to these APIs.

We'll provide an overview, updates, and roadmap for various NVIDIA video technologies. These include video SDK for encode and decode, and capture SDK for screen capture and application capture. NVIDIA's video SDK is a set of APIs for hardware-accelerated video encoding and decoding using NVIDIA GPUs. We'll provide an overview of the APIs, with particular emphasis on the latest features, such as FFMPEG/libAV support of NVIDIA-accelerated transcoding, motion-estimation API enhancements, quality and performance enhancements, and new codec support. Capture SDK is a set of APIs provided by NVIDIA for fast capture of the desktop screen or application buffer content. We'll provide an overview of the latest additions to these APIs.

  Back
 
Topics:
Video and Image Processing, Data Center and Cloud Infrastructure, Media and Entertainment
Type:
Tutorial
Event:
GTC Silicon Valley
Year:
2017
Session ID:
S7111
Download:
Share: