Hacker News with Generative AI: Video Processing

Don't Look Twice: Faster Video Transformers with Run-Length Tokenization (rccchoudhury.github.io)
We present Run-Length Tokenization (RLT), a simple and efficient approach to speed up video transformers by removing redundant tokens from the input.

Computer Vision, Machine Learning, Video Processing, Deep Learning, Transformers

74 points by jasondavies 5 days ago | 16 comments

Generating high-quality thumbnails from videos (apple.com)

Video Processing, Image Generation, Machine Learning

51 points by Austin_Conlon 11 days ago | 11 comments

Show HN: FFmpeg-over-IP – Connect to remote FFmpeg servers (github.com/steelbrain)
Connect to remote ffmpeg servers. Are you tired of unsuccessfully trying to pass your GPU through to a docker container running in a VM? So was I! ffmpeg-over-ip allows you to run an ffmpeg server on a machine with access to a GPU (Linux, Windows, or Mac) and connect to it from a remote machine. The only thing you need is Node.js installed and a shared filesystem (could be NFS, SMB, etc.) between the two machines.

Software, Video Processing, Remote Access, Docker

147 points by steelbrain 48 days ago | 72 comments

Video segmentation with Segment Anything 2 (SAM2) (roboflow.com)

Computer Vision, Video Processing, Generative AI, Machine Learning

32 points by SkalskiP 111 days ago | 3 comments

StreamPot: Run FFmpeg as an API with fluent-FFmpeg compatibility, queues and S3 (github.com/StreamPot)

API, Video Processing, FFmpeg, Cloud Storage, Software

218 points by thunderbong 116 days ago | 36 comments

Texture Enhancement for Video Super-Resolution (github.com/DachunKai)

Computer Vision, Video Processing, Deep Learning

179 points by smusamashah 149 days ago | 31 comments

The challenge of writing a on-demand transcoder (zoriya.dev)

Software Development, Video Processing, Technical Challenges

50 points by zoriya 160 days ago | 10 comments

Show HN: ffmpeg-english "capture from /dev/video0 every 1 second to jpg files" (github.com/dheera)