msu-video-group/memfof
[ICCV'2025 Highlight] MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
This tool helps computer vision engineers and researchers accurately estimate motion between frames in Full HD video sequences, even with limited GPU memory. You provide a video, and it outputs detailed optical flow maps showing how objects or pixels move across consecutive frames. This is ideal for anyone working on video analysis tasks like action recognition, object tracking, or video stabilization.
Use this if you need to analyze movement in high-resolution videos (Full HD or similar) and want to achieve high accuracy without demanding excessive GPU memory.
Not ideal if your primary goal is real-time processing on very low-power devices, or if you only work with low-resolution video where memory efficiency isn't a major concern.
Stars
87
Forks
3
Language
Python
License
BSD-3-Clause
Category
Last pushed
Dec 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/msu-video-group/memfof"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.