• Stars
    star
    756
  • Rank 60,048 (Top 2 %)
  • Language
    Python
  • License
    GNU General Publi...
  • Created over 4 years ago
  • Updated over 3 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

DeepFaceDrawing: Deep Generation of Face Images from Sketches

One version of our system is implemented using the Jittor, and you need to install Jittor first. We will also provide a version in pytorch.

HomePage: http://www.geometrylearning.com/DeepFaceDrawing/

Teaser Image

Abstract

Recent deep image-to-image translation techniques allow fast generation of face images from freehand sketches. However, existing solutions tend to overfit to sketches, thus requiring professional sketches or even edge maps as input. To address this issue, our key idea is to implicitly model the shape space of plausible face images and synthesize a face image in this space to approximate an input sketch. We take a local-to-global approach. We first learn feature embeddings of key face components, and push corresponding parts of input sketches towards underlying component manifolds defined by the feature vectors of face component samples. We also propose another deep neural network to learn the mapping from the embedded component features to realistic images with multi-channel feature maps as intermediate results to improve the information flow. Our method essentially uses input sketches as soft constraints and is thus able to produce high-quality face images even from rough and/or incomplete sketches. Our tool is easy to use even for non-artists, while still supporting fine-grained control of shape details. Both qualitative and quantitative evaluations show the superior generation ability of our system to existing and alternative solutions. The usability and expressiveness of our system are confirmed by a user study.

Prerequisites

  1. System

ใ€€- Ubuntu 16.04 or later

ใ€€- NVIDIA GPU + CUDA 9.2

  1. Software

ใ€€- Python 3.7

ใ€€- Jittor. More details in Jittor

sudo apt install python3.7-dev libomp-dev

sudo python3.7 -m pip install git+https://github.com/Jittor/jittor.git

python3.7 -m jittor.test.test_example

ใ€€- Packages

sh install.sh

How to use

Drawing sketch using DeepFaceDrawing GUI. Please download the pre-trained model[Baidu(Password:wiu9)] or [Google Drive], then put those under 'Param'.

python3.7 demo.py

Citation

If you found this code useful please cite our work as:

@article{chenDeepFaceDrawing2020,
    author = {Chen, Shu-Yu and Su, Wanchao and Gao, Lin and Xia, Shihong and Fu, Hongbo},
    title = {{DeepFaceDrawing}: Deep Generation of Face Images from Sketches},
    journal = {ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH  2020)},
    year = {2020},
    volume = 39,
    pages = {72:1--72:16},
    number = 4
}

More Repositories

1

DeepFaceEditing-Jittor

Python
282
star
2

NeRF-Editing

[CVPR 2022] Code for "NeRF-Editing: Geometry Editing of Neural Radiance Fields"
C++
186
star
3

NeUDF

The code for "NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering (CVPR 2023)"
Python
153
star
4

StylizedNeRF

[CVPR 2022] Code for StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D mutual learning
Python
142
star
5

DeepFaceVideoEditing

Python
110
star
6

SketchFaceNeRF

Python
102
star
7

DSG-Net

Code for 'DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation'
Python
84
star
8

NeRFFaceLighting

[TOG'23] NeRFFaceLighting: Implicit and Disentangled Face Lighting Representation Leveraging Generative Prior in Neural Radiance Fields
Jupyter Notebook
76
star
9

OctField

Code for "OctField: Hierarchical Implicit Functions for 3D Modeling (NeurIPS 2021)"
Python
61
star
10

IBSR_jittor

Code for 'Single Image 3D Shape Retrieval via Cross-Modal Instance and Category Contrastive Learning', ICCV 2021
Python
52
star
11

SketchDream

Python
43
star
12

RisaNET

Code for "RISA-Net: Rotation-Invariant and Structure-Aware Network for Fine-grained 3D Shape Retrieval"
Python
40
star
13

PRS-Net

Python
34
star
14

TM-NET

Python
33
star
15

MeshPooling

Code for 'Mesh Variational Autoencoders with Edge Contraction Pooling'
Python
33
star
16

RGBDNeRF

Code for "Neural Radiance Fields from Sparse RGB-D Images for High-Quality View Synthesis"
Python
27
star
17

NeRFFaceEditing

[SIGGRAPH Asia'22] NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fields
Jupyter Notebook
25
star
18

MeshVAE_neural_editing

Python
24
star
19

NEURALSLICE

The code of "NEURALSLICE: Neural 3D Triangle Mesh Reconstruction via Slicing 4D Tetrahedral Meshes (ICML 2023)"
Roff
23
star
20

TM-NET-Jittor

Python
20
star
21

PRS-NET-Jittor

Python
20
star
22

Stylemotion

Python
19
star
23

Farthestsampling

Furthest sampling and Voronoi sampling on 3D mesh
C++
19
star
24

DynamicHumanGeneration_Jittor

Python
17
star
25

intrinsicSym-Jittor

C++
17
star
26

HSDF-Net

The code for "HSDF: Hybrid Sign and Distance Field for Modeling Surfaces with Arbitrary Topologies (NeurIPS 2022)"
Python
15
star
27

MT_DE-Jittor

Python
13
star
28

PRS-Net_stamp

Python
12
star
29

GLIM-Net

Python
2
star
30

Fungal_Keratitis_Classification

Python
1
star