#450 · Primary category： Computer Vision
LiteFlowNet
LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)
Project last updated：03/21/23
GitHub Stars
632
Forks
104
Contributors
1
License
Other
Why we included this project
Anyone working on motion estimation in video will find LiteFlowNet a solid reference point. It's the official release of the CVPR 2018 network, with trained models, inference code, and the Caffe definition needed to reproduce the published KITTI results or adapt the architecture to your own frame-to-frame correspondence tasks. The design is compact and fast without sacrificing accuracy, which makes it a good fit for dense optical flow on constrained hardware or in latency-sensitive pipelines. The repo also documents the follow-up LiteFlowNet2, so you can compare the original approach with the later refinement. For teams benchmarking learned optical flow methods, it remains a convenient baseline.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)