liuguoyou

DeepMCBM

"A Deep Moving-camera Background Model" [Erez, Shapira Weber, and Freifeld, ECCV 2022]

Diff-Protect

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

DLGSANet

DQ-Det

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

facefusion

Next generation face swapper and enhancer

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

inswapper

One-click Face Swapper and Restoration powered by insightface 🔥

LiteTrack

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

MARLIN

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

MOS-Multi-Task-Face-Detect

Code for BMVC2021 "MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation"

MVT

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

norfair

Lightweight Python library for adding real-time multi-object tracking to any detector.

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

PIE

PMN

[TPAMI 2023 / ACMMM 2022 Best Paper Runner-Up Award] Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling (a Data Perspective)

Portrait-Mode-Video

Video dataset dedicated to portrait-mode video recognition.

ProPainter

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

qd-driver-activity-reco

ROMTrack

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

Self-Supervised-Metrical-Structure

STAR

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

taesd

Tiny AutoEncoder for Stable Diffusion

TeViS

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

ZoeDepth

Metric depth estimation from a single image