luorix1/unofficial-3D-VAN

Unofficial PyTorch implementation of 3D-VAN (https://arxiv.org/pdf/2212.02398.pdf)

Guide on how to use this repository

AdaIN

Download models

Download decoder.pth/vgg_normalized.pth and put them under models/.

Sanity check

Use --content and --style to provide the respective path to the content and style image. Run the following code to test

CUDA_VISIBLE_DEVICES=<gpu_id> python tests/test_AdaIN.py --content tests/input/cornell.jpg --style tests/style/woman_with_hat_matisse.jpg

Short descriptions of the modules used

Texformer: 3D Human Texture Estimation from a Single Image with Transformers

This code adapts the official implementation of "3D Human Texture Estimation from a Single Image with Transformers", ICCV 2021 (Oral)

References

[1] "3D Human Pose, Shape and Texture from Low-Resolution Images and Videos", IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.

[2] "3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning", ECCV, 2020

[3] "SMPL: A Skinned Multi-Person Linear Model", SIGGRAPH Asia, 2015

[4] "Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising", IEEE Transactions on Image Processing, 2020.

[5] "Learning Factorized Weight Matrix for Joint Filtering", ICML, 2020

[6] "Style normalization and restitution for generalizable person re-identification", CVPR, 2020

[7] "3D Human Texture Estimation from a Single Image with Transformers", ICCV 2021 (Oral)

[8] "Arbitraty Style Transfer in Real-time with Adaptive Instance Normalization", ICCV 2017 (Oral)