Cross-modal Deep Face Normals with Deactivable Skip Connections

Last update: Nov 27, 2022

Related tags

Deep Learning face_normals

Overview

Cross-modal Deep Face Normals with Deactivable Skip Connections

Victoria Fernández Abrevaya*, Adnane Boukhayma*, Philip H. S. Torr, Edmond Boyer (*Equal contrib.).
CVPR 2020 (Oral)

Requirements

Python 2.7
PyTorch 0.3

Data preprocessing

Input images are assumed to be crops of fixed size around the face. Using dlib, this command finds the tightest rectangular box of edge size l containing the face. Images are then cropped with a square patch of size 1.2xl. Input images are located in data/original and cropped images are saved in data/cropped.

Download the dlib trained facial shape predictor. Put file shape_predictor_68_face_landmarks.dat in directory data.

python crop.py

Testing

Download the model weights. Put file model.pth in directory data.

Run the following command to generate an image of normals from a cropped RGB image example in data/cropped. Results are saved in data/output.

python tester.py

Citation

@InProceedings{Abrevaya_2020_CVPR,
author = {Abrevaya, Victoria Fernandez and Boukhayma, Adnane and Torr, Philip H.S. and Boyer, Edmond},
title = {Cross-Modal Deep Face Normals With Deactivable Skip Connections},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}

Acknowledgement

This work was partly supported by the ERC grant ERC-2012-AdG 321162-HELIOS, the EPSRC grant Seebibyte EP/M013774/1 and the EPSRC/MURI grant EP/N019474/1.

License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

You might also like...

Official Implement of CVPR 2021 paper “Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting”

RGBT Crowd Counting Lingbo Liu, Jiaqi Chen, Hefeng Wu, Guanbin Li, Chenglong Li, Liang Lin. "Cross-Modal Collaborative Representation Learning and a L

37 Dec 8, 2022

Comments

Problem z uruchomieniem

Nie mogę uruchomić pliku tester.py, podaje błąd:

Traceback (most recent call last): File "C:\Users\tward\Documents\git\face_normals\tester.py", line 4, in from resnet_unet import ResNetUNet File "C:\Users\tward\Documents\git\face_normals\resnet_unet_init_.py", line 1, in from .resnet_unet_model import ResNetUNet File "C:\Users\tward\Documents\git\face_normals\resnet_unet\resnet_unet_model.py", line 3, in from resnet import resnet18 File "C:\Python310\lib\site-packages\resnet_init_.py", line 1, in from keras.applications.resnet50 import ResNet50 ModuleNotFoundError: No module named 'keras.applications.resnet50'

opened by twardy9303 5
paper+PRNet operation question

The PRNet can extract the verts for the face. This paper improves the PRNet results means adding vert norms,and do not change the verts' positions? So,I can construct an obj file like that: v、f、texture get from PRNet vn get from this paper Am I right?

opened by 1165048017 6
Training Code

Hi,@boukhayma,thanks for your amazing work,and I'm very interested to your work,but the training details I can't understand，so it is difficult for me to implement the training code.Could you share me the training code? My email: [email protected]

Very appreciated if you can reply to me.

opened by dafuny 0

Cross-modal Deep Face Normals with Deactivable Skip Connections

Related tags

Overview

Cross-modal Deep Face Normals with Deactivable Skip Connections

Requirements

Data preprocessing

Testing

Citation

Acknowledgement

License

You might also like...

Official Implement of CVPR 2021 paper “Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting”

Pytorch code for ICRA'21 paper: "Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation"

X-modaler is a versatile and high-performance codebase for cross-modal analytics.

ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration

Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021

A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval

SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks (Scientific Reports)

[ICCV 2021 Oral] SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer

Realtime Face Anti Spoofing with Face Detector based on Deep Learning using Tensorflow/Keras and OpenCV

Comments

Problem z uruchomieniem

paper+PRNet operation question

Training Code

Owner

PyTorch code for the paper "Complementarity is the King: Multi-modal and Multi-grained Hierarchical Semantic Enhancement Network for Cross-modal Retrieval".

CVPR 2021 Official Pytorch Code for UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

Source code of the paper PatchGraph: In-hand tactile tracking with learned surface normals.

ICON: Implicit Clothed humans Obtained from Normals (CVPR 2022)

Cross Quality LFW: A database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments

Flexible-Modal Face Anti-Spoofing: A Benchmark

《Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis》(2021)

Code for Referring Image Segmentation via Cross-Modal Progressive Comprehension, CVPR2020.

Probabilistic Cross-Modal Embedding (PCME) CVPR 2021

Cross-Modal Contrastive Learning for Text-to-Image Generation