liuguoyou

MobileSAM-pytorch

Reproduction of MobileSAM using pytorch

ASwin-Video-Denoising

BiMatting

This project is the official implementation of our accepted NeurIPS 2023 paper BiMatting: Efficient Video Matting via Binarization.

BVI-VFI-database

[IEEE TIP'2023] "BVI-VFI: A Video Quality Database for Video Frame Interpolation", Duolikun Danier, Fan Zhang, David Bull

Diff-Protect

🛡️ Code repo for paper: Toward effective protection against diffusion-based mimicry through score distillation

DQ-Det

Codes for ICML 2023 Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation

FastLLVE

FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table (ACM MM 2023)

graphics2raw

Code associated with our paper "Graphics2RAW: Mapping Computer Graphics Images to Sensor RAW Images". The paper has been accepted to the International Conference on Computer Vision (ICCV'23).

image-background-remove-tool

✂️ Automated high-quality background removal framework for an image using neural networks. ✂️

instructor-embedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

LiteTrack

A fast and high-performance visual object tracker with real-time speed on Jetson.

LLF

low-light-video-enhancement

Temporally Consistent Enhancement of Low-light Videos via Spatial-Temporal Compatible Learning

MARLIN

[CVPR] MARLIN: Masked Autoencoder for facial video Representation LearnINg

Metric3D

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image"

modular-memorability

Official implementation for the CVPR 2023 paper "Modular memorability: tiered representations for video memorability prediction"

MVT

[BMVC 2023] Mobile Vision Transformer-based Visual Object Tracking

omnimotion

OpenSeeFace

Robust realtime face and facial landmark tracking on CPU with Unity integration

PARIMA

PARIMA is a viewport adaptive 360-degree video streaming algorithm that takes into account the prime object trajectories as well as the head movement logs to predict the future viewports accurately

Portrait-Mode-Video

Video dataset dedicated to portrait-mode video recognition.

ProPainter

[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

ROMTrack

[ICCV 2023] Robust Object Modeling for Visual Tracking, Official Implementation

Self-Supervised-Metrical-Structure

ssmnet_ISMIR2023

STAR

[CVPR 2023] STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection

taesd

Tiny AutoEncoder for Stable Diffusion

video_depth

VisDrone-Dataset

The dataset for drone based detection and tracking is released, including both image/video, and annotations.

ViTMatte

Boosting Image Matting with Pretrained Plain Vision Transformers