刘国友's repositories
Depth-Anything-V2
Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
360-image-optical-flow
Optical flow calculation for 360 images
amodal-optical-flow
Official implementation for "Amodal Optical Flow" (ICRA 2024).
baseboostdepth
[BMVC'24] BaseBoostDepth: Exploiting Larger Baselines For Self-supervised Monocular Depth Estimation
boxmot
BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models
Depth-Anything
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
hdr-plus-swift
📸Night mode on any camera. Based on HDR+.
HDR_Toolbox
HDR Toolbox for processing High Dynamic Range (HDR) images into MATLAB and Octave
Lightweight-Deformable-GS
[Just 4 Fun] Deformable-GS with less storage, 150+FPS, and sota quality.
Lightweight-Face-Detector-Pruning
Code and pruned models for our paper: K. Gkrispanis, N. Gkalelis, V. Mezaris, "Filter-Pruning of Lightweight Face Detectors Using a Geometric Median Criterion", Proc. IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW 2024), Waikoloa, Hawaii, USA, Jan. 2024.
NGD-SLAM
NGD-SLAM: Towards Real-Time SLAM for Dynamic Environments without GPU.
norfair-tracking
Lightweight Python library for adding real-time multi-object tracking to any detector.
open_vins
An open source platform for visual-inertial navigation research.
PSENet-Image-Enhancement
PSENet: Progressive Self-Enhancement Network for Unsupervised Extreme-Light Image Enhancement (WACV 2023)
R2LCM
[CVPR'23/IJCV'24] Raw Image Reconstruction with Learned Compact Metadata
stream-vc
An unofficial PyTorch implementation of the StreamVC(Real-Time Low-Latency Voice Conversion)
tartanvo
TartanVO: A Generalizable Learning-based VO
tinyCLAP
Implementation of tinyCLAP.
UDU
[ECCV'24] Unrolled Decomposed Unpaired Learning for Controllable Low-Light Video Enhancement
VideoLingo
Netflix级字幕切割翻译、精确对齐和个性化配音,一键全自动视频搬运