All Projects → rubelchowdhury20 → Neural-Re-Rendering-of-Humans-from-a-Single-Image

rubelchowdhury20 / Neural-Re-Rendering-of-Humans-from-a-Single-Image

Licence: MIT License
Pytorch implementation of the paper, Neural re-rendering of humans from a single image.

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Neural-Re-Rendering-of-Humans-from-a-Single-Image

ainized-detectron2
api server for detectron2
Stars: ✭ 22 (-71.43%)
Mutual labels:  detectron2
InstanceShadowDetection
Instance Shadow Detection (CVPR 2020)
Stars: ✭ 97 (+25.97%)
Mutual labels:  detectron2
detectron2-pipeline
Modular image processing pipeline using OpenCV and Python generators powered by Detectron2.
Stars: ✭ 78 (+1.3%)
Mutual labels:  detectron2
MPViT
MPViT:Multi-Path Vision Transformer for Dense Prediction in CVPR 2022
Stars: ✭ 193 (+150.65%)
Mutual labels:  detectron2
Entity
EntitySeg Toolbox: Towards Open-World and High-Quality Image Segmentation
Stars: ✭ 313 (+306.49%)
Mutual labels:  detectron2
ClothingTransfer-NCNN
CT-Net, OpenPose, LIP_JPPNet, DensePose running with ncnn⚡服装迁移/虚拟试穿⚡ClothingTransfer/Virtual-Try-On⚡
Stars: ✭ 166 (+115.58%)
Mutual labels:  densepose
detectron2 backbone
detectron2 backbone: resnet18, efficientnet, hrnet, mobilenet v2, resnest, bifpn
Stars: ✭ 171 (+122.08%)
Mutual labels:  detectron2
ai-background-remove
Cut out objects and remove backgrounds from pictures with artificial intelligence
Stars: ✭ 70 (-9.09%)
Mutual labels:  detectron2
denseposeInstalltion
How to Install DensePose
Stars: ✭ 20 (-74.03%)
Mutual labels:  densepose
point based clothing
Official PyTorch code for the paper: "Point-Based Modeling of Human Clothing" (ICCV 2021)
Stars: ✭ 57 (-25.97%)
Mutual labels:  virtual-try-on
ACGPN
"Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content",CVPR 2020. (Modified from original with fixes for inference)
Stars: ✭ 48 (-37.66%)
Mutual labels:  virtual-try-on
DA-RetinaNet
Official Detectron2 implementation of DA-RetinaNet of our Image and Vision Computing 2021 work 'An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites'
Stars: ✭ 31 (-59.74%)
Mutual labels:  detectron2
GDR-Net
GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation. (CVPR 2021)
Stars: ✭ 167 (+116.88%)
Mutual labels:  detectron2
BCNet
Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]
Stars: ✭ 434 (+463.64%)
Mutual labels:  detectron2
EverybodyDanceNow reproduce pytorch
Everybody dance now reproduced in pytorch
Stars: ✭ 579 (+651.95%)
Mutual labels:  pix2pixhd
Yet-Another-Anime-Segmenter
Instance segmentation for anime characters based on CondInst and SOLOv2
Stars: ✭ 171 (+122.08%)
Mutual labels:  detectron2
HJDataset
A Large Dataset of Historical Japanese Documents with Complex Layouts
Stars: ✭ 19 (-75.32%)
Mutual labels:  detectron2

Neural Re-rendering of Humans from a Single Image

Paper

The code was implemented for the Garment Transfer obejctive, where top cloth of the source image was rendered on the target image.

The improvement of the code with the hyper-parameter tunings are under process. The inferenece code with better results will be updated soon.

Results:

Sample Results from training using the LIP dataset:

result_1 result_2

Architecture:

architecture

Dataset:

The LIP dataset(Image-based Multi-pose Virtual Try On) was used to train the model.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].