quziyan / Post-Processing-for-Matting
We often change background after matting. But due to the matting precision, the edge of body, especially hair, often leak pixels contain background, so we need some post-processing like this.
☆13Updated 3 years ago
Related projects: ⓘ
- ☆12Updated 4 years ago
- ☆51Updated 3 years ago
- ☆62Updated this week
- ☆42Updated 2 years ago
- A large-scale face dataset for hair segmentation, hair recognition, and GANs for hair generation and editing.☆75Updated 3 years ago
- Re-implementation of e4e that use mobilenet-v3 and stylegan2-1024p☆29Updated last year
- The official repository for Deep Image Matting with Flexible Guidance Input☆58Updated 2 years ago
- Some portrait matting models designed for mobile device.☆16Updated 5 years ago
- A reimplementation of the CVPR2019 paper *Learning-based Sampling for Natural Image Matting*.☆24Updated 4 years ago
- Official implementation of VCIP 2020 paper: "Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decompo…☆27Updated 3 years ago
- PyTorch implementation of Google's Mediapipe model. Iris Landmark model | Face Mesh Model☆39Updated 3 years ago
- Regress Face Attributes with MobileNetV2☆40Updated 4 years ago
- ☆19Updated 2 years ago
- PyTorch code for "Semi-parametric Makeup Transfer via Semantic-aware Correspondence"☆34Updated 2 years ago
- Facial Sketch Render, ICASSP 2021☆27Updated 3 years ago
- The PyTorch implement of the paper "Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution …☆42Updated 4 years ago
- Face alignment,Facial Landmark detection ,ACM Multimedia Conference 2020☆13Updated last year
- A pre-trained face parser based on SegNeXt☆44Updated last year
- ☆10Updated 3 years ago
- [ACM MM 2023] KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration☆9Updated 9 months ago
- double-chin-dataset is a high-quality image dataset of double chin removal, based on StyleGAN.☆33Updated 5 months ago
- ☆17Updated 3 years ago
- A pytorch implementation of "Robust Facial Landmark Detection by Multi-order Multi-constrained Network"☆13Updated 3 years ago
- faceshifter训练不稳定,通过使用stylegan2,对latents进行attrloss和idloss,会使得稳定性大大增加。而且可以产生更高分辨率和平滑的图像。☆15Updated 3 years ago
- Mega list of face related datasets☆28Updated 4 years ago
- [AAAI 2022] This is the official pytorch code for SSAT: A Symmetric Semantic-Aware Transformer Network for Makeup Transfer and Removal☆84Updated 4 months ago
- Heatmap Regression via Randomized Rounding☆50Updated 2 years ago
- StyleGAN2 Distillation for Feed-forward Image Manipulation☆24Updated 4 years ago
- ☆45Updated 2 years ago
- A python implementation of portrait lighting transfer using a mass transport approach.☆35Updated 2 years ago