prehoke

prehoke

Geek Repo

Github PK Tool:Github PK Tool

prehoke's starred repositories

douyin

Vue3 + Pinia 仿抖音,Vue 在移动端的最佳实践 . Imitate TikTok ,Vue Best practices on Mobile

Language:VueLicense:GPL-3.0Stargazers:9725Issues:0Issues:0

BEVFormer_tensorrt

BEVFormer inference on TensorRT, including INT8 Quantization and Custom TensorRT Plugins (float/half/half2/int8).

Language:PythonLicense:Apache-2.0Stargazers:429Issues:0Issues:0

AccuMO

[MobiCom '23] AccuMO: Accuracy-Centric Multitask Offloading in Edge-Assisted Mobile Augmented Reality

Language:C++License:MITStargazers:12Issues:0Issues:0

AnimateAnyone

Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation

License:Apache-2.0Stargazers:14487Issues:0Issues:0

motionshop

Project page of replacing the human motion in the video with a virtual 3D human

Stargazers:388Issues:0Issues:0

FFC

This is an official pytorch implementation of Fast Fourier Convolution.

Language:PythonLicense:Apache-2.0Stargazers:345Issues:0Issues:0

Awesome-Image-Inpainting

A curated list of image inpainting and video inpainting papers and resources

Language:PythonStargazers:1884Issues:0Issues:0
Language:PythonStargazers:1Issues:0Issues:0

yiqinzhao.me-source

Source code for yiqinzhao.me

Stargazers:1Issues:0Issues:0

special_assignment_2020

Special Assignment - Spring 2020 IoT and Fog computing

Language:PythonStargazers:7Issues:0Issues:0

ICLR2023-OpenReviewData

ICLR 2023 Paper submission analysis from https://openreview.net/group?id=ICLR.cc/2023/Conference

Language:Jupyter NotebookStargazers:101Issues:0Issues:0

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

License:Apache-2.0Stargazers:1Issues:0Issues:0

Track-Anything

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Language:PythonLicense:MITStargazers:6495Issues:0Issues:0

Mediapipe-python-pose-assessment

基于Mediapipe的人体姿态识别与匹配计算

Language:PythonStargazers:17Issues:0Issues:0

HolisticBarracuda

HolisticBarracuda is the Unity Package that simultaneously estimates 33 pose, 21 per-hand, and 468 facial landmarks on the Unity Barracuda with GPU.

Language:C#License:Apache-2.0Stargazers:106Issues:0Issues:0

Pose-Network

Sign Language is detected in realtime using video sequences. Our approach involves MediaPipe Holistic for keypoints extraction and LSTM Model for prediction.

Language:PythonLicense:MITStargazers:26Issues:0Issues:0

BlazePoseBarracuda

Tracking Body Landmark using Google MediaPipe BlazePose Model in Unity Barracuda

Language:C#License:Apache-2.0Stargazers:44Issues:0Issues:0

Tokyo2020-Pictogram-using-MediaPipe

MediaPipeで姿勢推定を行い、Tokyo2020オリンピック風のピクトグラムを表示するデモ

Language:PythonLicense:Apache-2.0Stargazers:303Issues:0Issues:0

3D-landmarks-Pose_estimation

predicting of 3d landmarks using Blazepose and Detectrin2 model base on 2d video by Python

Language:Jupyter NotebookStargazers:2Issues:0Issues:0

MediapipeUnityProject

3D pose recognition using Mediapipe and visualized using Unity.

Language:C#Stargazers:7Issues:0Issues:0

Body-Pose-Tracking

Body Pose estimation ,tracking using OpenCv and mediapipe

Language:Jupyter NotebookStargazers:4Issues:0Issues:0

PyMAF-X

[TPAMI 2023] PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images

Language:PythonLicense:NOASSERTIONStargazers:224Issues:0Issues:0

MotionBERT

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

Language:PythonLicense:Apache-2.0Stargazers:1067Issues:0Issues:0

Explicit-Visual-Prompt

[CVPR 2023] Explicit Visual Prompting for Low-Level Structure Segmentations

Language:PythonLicense:BSD-3-ClauseStargazers:190Issues:0Issues:0

ONNX-MST-Image-Inpainting

Python scripts for performing Image Inpainting using the MST model in ONNX

Language:PythonLicense:MITStargazers:14Issues:0Issues:0

Python_Grpc_VideoStream_Sample

The Streams Camera Capture for Python Grpc Samples

Language:PythonLicense:MITStargazers:14Issues:0Issues:0

X-Avatar

X-Avatar: Expressive Human Avatars (CVPR2023)

Language:PythonLicense:NOASSERTIONStargazers:380Issues:0Issues:0

openh264

Open Source H.264 Codec

Language:C++License:BSD-2-ClauseStargazers:5562Issues:0Issues:0

iOS_DualCam_MultiSensor

an app that simultaneously record videos of dual cameras, Depth maps and sensor data from multiple sensors.

Language:SwiftStargazers:7Issues:0Issues:0