HongHu's starred repositories
LLM-in-Vision
Recent LLM-based CV and related works. Welcome to comment/contribute!
MiniGPT4-video
Official code for MiniGPT4-video
Awesome-LLM4AD
A curated list of awesome LLM for Autonomous Driving resources (continually updated)
YOLO-World
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
Upscale-A-Video
Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution
Illumination-Adaptive-Transformer
[BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-processing.
RetinexNet
A Tensorflow implementation of RetinexNet
Simple-Align
https://arxiv.org/abs/2402.18929
Inpaint-Anything
Inpaint anything using Segment Anything and inpainting models.
X-AnyLabeling
Effortless data labeling with AI support from Segment Anything and other awesome models.
GazeCapture
Eye Tracking for Everyone