Starred repositories
It is a simple python tool to extract key-frames from a video file using peak estimation from frame difference.
A Benchmark Suite for Shot Sequence Ordering in AI-Assisted Video Editing
5
Updated Oct 9, 2025
[CVPR 2025] Official Repository of the paper "On the Consistency of Video Large Language Models in Temporal Comprehension"
[ICCV2025 Highlight] Stereo Any Video: Temporally Consistent Stereo Matching
Deep based Visual SLAM Project(Depth estimation, Optical flow, Visual inertial odometry)
An unofficial pytorch implementation of "STREAMVC: REAL-TIME LOW-LATENCY VOICE CONVERSION".
Optical flow calculation for 360 images
Code related to the paper "MobileMEF: Fast and Efficient Method for Multi-Exposure Fusion"
This framework includes the loading of different datasets as well as several denoising models. Several of the models are optimized for mobile usage. Those models include a simple U-Net, the winning…
Ocean is the in-house framework for Computer Vision (CV) and Augmented Reality (AR) applications at Meta. It is platform independent and is mainly implemented in C/C++.
Joint RGB-Spectral Decomposition Model Guided Image Enhancement in Mobile Photography (ECCV2024)
[IJCV 2026] FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds. AI拟音大师，给你的无声视频添加生动而且同步的音效 😝
OpenStereo: A Comprehensive Benchmark for Stereo Matching
[CVPR 2024] MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos
This repository contains the official implementation of the research papers, "MobileCLIP" CVPR 2024 and "MobileCLIP2" TMLR August 2025
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Official code implementation of Vary-toy (Small Language Model Meets with Reinforced Vision Vocabulary)
[ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
Emo-CLIM: Emotion-Aligned Contrastive Learning Between Images and Music [ICASSP 2024]
Code for "Simple Pooling Front-ends for Efficient Audio Calssification", ICASSP 2023
【CVPR'24】OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
Official implementations for paper: LivePhoto: Real Image Animation with Text-guided Motion Control