Typography Research Collection

# Typography Research Collection [[hackmd]](https://hackmd.io/s/B1BZCZpPX)[[github]](https://github.com/IShengFang/TypographyResearchCollection)[[github pages]](https://ishengfang.github.io/TypographyResearchCollection/) Typography is the cross between technology and liberal arts. This page is a research collection that includes computer graphics, computer vision, machine learning that related to typography. ## Visual Text Generation and Editing - **Generate Like Experts: Multi-Stage Font Generation by Incorporating Font Transfer Process into Diffusion Models** - Bin Fu, Fanghua Yu, Anran Liu, Zixuan Wang, Jie Wen, Junjun He, Yu Qiao - CVPR 2024 - **VecFusion: Vector Font Generation with Diffusion** - Vikas Thamizharasan, Difan Liu, Shantanu Agarwal, Matthew Fisher, Michael Gharbi, Oliver Wang, Alec Jacobson, Evangelos Kalogerakis - CVPR 2024 - [[arxiv]](https://arxiv.org/abs/2312.10540) ![](https://arxiv.org/html/2312.10540v1/x2.png) - **FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning** - Zhenhua Yang, Dezhi Peng, Yuxin Kong, Yuyi Zhang, Cong Yao, Lianwen Jin - AAAI 2024 - [[project page]](https://yeungchenwa.github.io/fontdiffuser-homepage/)[[arxiv]](https://arxiv.org/abs/2312.12142)[[code]](https://github.com/yeungchenwa/FontDiffuser)[[demo]](https://huggingface.co/spaces/yeungchenwa/FontDiffuser-Gradio) ![](https://github.com/yeungchenwa/FontDiffuser/blob/main/figures/with_instructpix2pix.png?raw=true) - **AnyText: Multilingual Visual Text Generation And Editing** - Yuxiang Tuo, Wangmeng Xiang, Jun-Yan He, Yifeng Geng∗, Xuansong Xie - ICLR 2024 - [[paper]](https://arxiv.org/abs/2311.03054)[[code]](https://github.com/tyxsspa/AnyText?tab=readme-ov-file)[[demo]](https://modelscope.cn/studios/damo/studio_anytext/summary) ![](https://github.com/tyxsspa/AnyText/blob/main/docs/framework.jpg?raw=true) - **GlyphControl: Glyph Conditional Control for Visual Text Generation** - Yukang Yang, Dongnan Gui, Yuhui Yuan, Weicong Liang, Haisong Ding, Han Hu, Kai Chen - NeurIPS 2023 - [[paper]](https://arxiv.org/pdf/2305.18259.pdf)[[code]](https://github.com/AIGText/GlyphControl-release) ![](https://github.com/AIGText/GlyphControl-release/blob/main/readme_files/architecture-n.png?raw=true) - **DiffUTE: Universal Text Editing Diffusion Model** - Haoxing Chen, Zhuoer Xu1, Zhangxuan Gu*, Jun Lan, Xing Zheng, Yaohui Li, Changhua Meng, Huijia Zhu, Weiqiang Wang - ∗Corresponding author - NeurIPS 2023 - [[paper]](https://arxiv.org/abs/2305.10825)[[code]](https://github.com/chenhaoxing/DiffUTE/tree/main) ![](https://github.com/chenhaoxing/DiffUTE/blob/main/docs/ute.png?raw=true) - **TextDiffuser: Diffusion Models as Text Painters** - Jingye Chen*, Yupan Huang*, Tengchao Lv, Lei Cui, Qifeng Chen, Furu Wei - *Equal Contribution - NeurIPS 2023 - [[project page]](https://jingyechen.github.io/textdiffuser/)[[paper]](https://arxiv.org/abs/2305.10855)[[code]](https://github.com/microsoft/unilm/tree/master/textdiffuser)[[demo]](https://huggingface.co/spaces/JingyeChen22/TextDiffuser)[[colab]](https://colab.research.google.com/drive/115Qw0l5dhjlTtrbywMWRwhz9IxKE4_Dg?usp=sharing) ![](https://jingyechen.github.io/textdiffuser/static/images/architecture.jpg) - **GlyphDraw: Learning to Draw Chinese Characters in Image Synthesis Models Coherently** - Jian Ma, Mingjun Zhao, Chen Chen, Ruichen Wang, Di Niu, Haonan Lu, Xiaodong Lin - arxiv 2023 - [[project page]](https://1073521013.github.io/glyph-draw.github.io/)[[paper]](https://arxiv.org/abs/2303.17870)[[code]](https://github.com/1073521013/GlyphDraw) ![](https://1073521013.github.io/glyph-draw.github.io/img/example1.681b4aa6.png) - **DeepFloyd IF** - Inspired by "Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding", NeurIPS2022 - aka Imagen - [[code]](https://github.com/deep-floyd/IF?tab=readme-ov-file) ![](https://github.com/deep-floyd/IF/blob/develop/pics/deepfloyd_if_scheme.jpg?raw=true) - **Character-Aware Models Improve Visual Text Rendering** - arxiv - Rosanne Liu∗, Dan Garrette∗, Chitwan Saharia, William Chan, Adam Roberts, Sharan Narang, Irina Blok, RJ Mical, Mohammad Norouzi, Noah Constant∗ - *Equal contribution - [[paper]](https://arxiv.org/pdf/2212.10562.pdf) ![](https://hackmd.io/_uploads/B1zS_fZua.png) - **OCR-VQGAN: Taming Text-within-Image Generation** - Juan A. Rodríguez, David Vázquez, Issam Laradji, Marco Pedersoli, Pau Rodríguez - WACV2023 - [[paper(CVF)]](https://openaccess.thecvf.com/content/WACV2023/papers/Rodriguez_OCR-VQGAN_Taming_Text-Within-Image_Generation_WACV_2023_paper.pdf)[[paper(arxiv)]](https://arxiv.org/abs/2210.11248)[[code]](https://github.com/joanrod/ocr-vqgan) ![](https://github.com/joanrod/ocr-vqgan/raw/master/assets/ocr_v2.png) ## Font Stye Transfer and Glyph Generation ### NN Approach - **DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion** - Maham Tanveer, Yizhi Wang, Ali Mahdavi-Amiri, Hao Zhang - ICCV2023 - [[project page]](https://ds-fusion.github.io/)[[paper]](https://arxiv.org/abs/2303.09604)[[code]](https://github.com/tmaham/DS-Fusion) [[demo]](https://huggingface.co/spaces/tmaham/DS-Fusion-Express) ![](https://ds-fusion.github.io/static/images/ds-fusion.png) - **Word-As-Image for Semantic Typography** - Shir Iluz*, Yael Vinker*, Amir Hertz, Daniel Berio, Daniel Cohen-Or, Ariel Shamir - *Denotes equal contribution - SIGGRAPH 2023 - Honorable Mention Award - [[project page]](https://wordasimage.github.io/Word-As-Image-Page/)[[paper]](https://arxiv.org/abs/2303.01818)[[code]](https://github.com/WordAsImage/Word-As-Image)[[demo]](https://huggingface.co/spaces/SemanticTypography/Word-As-Image) ![](https://github.com/Shiriluz/Word-As-Image/raw/main/images/teaser.png) - **DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality** - Yuqing Wang, Yizhi Wang, Longhui Yu, Yuesheng Zhu, Zhouhui Lian - CVPR 2023 - [[paper(CVPR)]](https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_DeepVecFont-v2_Exploiting_Transformers_To_Synthesize_Vector_Fonts_With_Higher_Quality_CVPR_2023_paper.pdf)[[code]](https://arxiv.org/abs/2303.14585) ![](https://github.com/yizhiwang96/deepvecfont-v2/raw/main/statics/chinese_font_demo_syn_1.gif) - **DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learning** - Yizhi Wang, Zhouhui Lian - SIGGRAPH Asia 2021 - [[project page]](https://yizhiwang96.github.io/deepvecfont_homepage/)[[code]](https://github.com/yizhiwang96/deepvecfont)[[paper]](https://arxiv.org/abs/2110.06688) ![](https://yizhiwang96.github.io/deepvecfont_homepage/imgs/teaser.svg) - **StrokeStyles: Stroke-based Segmentation and Stylization of Fonts** - Daniel Berio, Frederic Fol Leymarie, Paul Asente, Jose Echevarria - ACM Transactions on GraphicsVolume 41Issue 3Article No.: 28pp 1–21 - [[paper]](https://dl.acm.org/doi/10.1145/3505246) - **DG-Font: Deformable Generative Networks for Unsupervised Font Generation** - Yangchen Xie, Xinyuan Chen, Li Sun, Yue Lu - [[paper(CVPR)]](https://openaccess.thecvf.com/content/CVPR2021/html/Xie_DG-Font_Deformable_Generative_Networks_for_Unsupervised_Font_Generation_CVPR_2021_paper.html)[[paper(arxiv)]](https://arxiv.org/abs/2104.03064)[[code]](https://github.com/ecnuycxie/DG-Font) - CVPR2021 ![](https://i.imgur.com/QLnHf6k.png) - **Multiple Heads are Better than One:Few-shot Font Generation with Multiple Localized Experts** - Song Park, Sanghyuk Chun, Junbum Cha, Bado Lee, Hyunjung Shim - [[paper]](https://arxiv.org/abs/2104.00887)[[code]](https://github.com/clovaai/mxfont) - ICCV 2021 ![](https://i.imgur.com/Pd1y67r.png) - **Font Style that Fits an Image -- Font Generation Based on Image Context** - [[paper]](https://arxiv.org/abs/2105.08879)[[code]](https://github.com/Taylister/FontFits) - Taiga Miyazono, Brian Kenji Iwana, Daichi Haraguchi, and Seiichi Uchida - arxiv 2021 ![](https://raw.githubusercontent.com/Taylister/FontFits/main/smaple/generated_example.png) - **Few-shot Font Generation with Localized Style Representations and Factorization** - Song Park*, Sanghyuk Chun*, Junbum Cha, Bado Lee, Hyunjung Shim1 - *: equal contribution - [[project page]](https://cvml.yonsei.ac.kr/projects/few-shot-font-generation) [[paper]](https://arxiv.org/abs/2009.11042)[[code]](https://github.com/clovaai/lffont) - AAAI 2021 ![](https://i.imgur.com/ZMjQCap.png) ![](https://i.imgur.com/lkEBLBG.png) - **Handwritten Chinese Font Generation with Collaborative Stroke Refinement** - [[paper]](https://arxiv.org/abs/1904.13268)[[WACV2021]](https://openaccess.thecvf.com/content/WACV2021/html/Wen_Handwritten_Chinese_Font_Generation_With_Collaborative_Stroke_Refinement_WACV_2021_paper.html)[[code(dead)]](https://github.com/s024/fontml-research) - Chuan Wen, Jie Chang, Ya Zhang, Siheng Chen, Yanfeng Wang, Mei Han, Qi Tian - WACV 2021 ![](https://i.imgur.com/7sDYLGj.png) ![](https://i.imgur.com/93RSv38.png) - **RD-GAN: Few/Zero-Shot Chinese Character Style Transfer via Radical Decomposition and Rendering** - Yaoxiong Huang, Mengchao He, Lianwen Jin, Yongpan Wang - [[paper(ECVA)]](https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/4880_ECCV_2020_paper.php) - ECCV 2020 ![](https://i.imgur.com/536F0HD.png) - **Few-shot Compositional Font Generation with Dual Memory** - Junbum Cha, Sanghyuk Chun, Gayoung Lee, Bado Lee, Seonghyeon Kim, Hwalsuk Lee. - [[paper]](https://arxiv.org/abs/2005.10510) [[code]](https://github.com/clovaai/dmfont) - ECCV 2020 ![](https://raw.githubusercontent.com/clovaai/dmfont/master/assets/teaser.jpg) ![](https://i.imgur.com/JKD8brf.png) ![](https://i.imgur.com/1cD2G3p.png) - **CalliGAN: Style and Structure-aware Chinese Calligraphy Character Generator** - [[paper]](https://arxiv.org/abs/2005.12500)[[code]](https://github.com/JeanWU/CalliGAN) - Shan-Jean Wu, Chih-Yuan Yang and Jane Yung-jen Hsu - AI for Content Creation Workshop CVPR 2020. ![](https://i.imgur.com/itv9IMn.png) - **A Learned Representation for Scalable Vector Graphics** - [[paper]](https://arxiv.org/abs/1904.02632) - Raphael Gontijo Lopes, David Ha, Douglas Eck, Jonathon Shlens - ICCV 2019 - ICLR workshop 2019 ![](https://user-images.githubusercontent.com/544269/61917345-9c587780-af87-11e9-96a7-cf406aaa4f97.png) - **Large-scale Tag-based Font Retrieval with Generative Feature Learning** - [[paper]](https://arxiv.org/abs/1909.02072)[[page]](https://www.cs.rochester.edu/u/tchen45/font/font.html) - Tianlang Chen, Zhaowen Wang, Ning Xu, Hailin Jin, Jiebo Luo - ICCV 2019 - **DynTypo: Example-based Dynamic Text Effects Transfer** - [[paper]](http://www.icst.pku.edu.cn/zlian/docs/2019-04/20190418093151169110.pdf) - Yifang Men, Zhouhui Lian, Yingmin Tang, Jianguo Xiao - CVPR 2019 - <iframe width="560" height="315" src="https://www.youtube.com/embed/FkFQ6bV1s-o" frameborder="0" allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> - **Typography with Decor: Intelligent Text Style Transfer** - Wenjing Wang, Jiaying Liu, Shuai Yang, and Zongming Guo - CVPR2019 - [[project page]](https://daooshee.github.io/Typography2019/) [[paper]](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Typography_With_Decor_Intelligent_Text_Style_Transfer_CVPR_2019_paper.pdf) [[code]](https://github.com/daooshee/Typography-with-Decor) ![](https://hackmd.io/_uploads/rkvrLQrWa.png) - **DeepGlyph** - [[websites]](https://deepglyph.app/) - <iframe width="560" height="315" src="https://www.youtube.com/embed/T70k-0qgccs" frameborder="0" allow="accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> - **Coconditional Autoencoding Adversarial Networks for Chinese Font Feature Learning** - [[paper]](https://arxiv.org/abs/1812.04451) - arxiv 2018 - Zhizhan Zheng, Feiyun Zhang - **TET-GAN: Text Effects Transfer via Stylization and Destylization** - [[paper]](https://www.aaai.org/ojs/index.php/AAAI/article/view/3919) - Shuai Yang, Jiaying Liu, Wenjing Wang, Zongming Guo - AAAI2019 ![](https://i.imgur.com/k31pWcZ.png) - **SCFont: Structure-Guided Chinese Font Generation via Deep Stacked Networks** - [[paper]](https://aaai.org/ojs/index.php/AAAI/article/view/4294) - Yue Jiang, Zhouhui Lian*, Yingmin Tang, Jianguo Xiao - AAAI 2019 ![](https://i.imgur.com/NzY6mF3.png) - **Separating Style and Content for Generalized Style Transfer** - [[paper]](http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Separating_Style_and_CVPR_2018_paper.html)[[code]](https://github.com/zhyxun/Separating-Style-and-Content-for-Generalized-Style-Transfer) - Yexun Zhang, Ya Zhang, Wenbin Cai - CVPR 2018 - Networks ![](https://raw.githubusercontent.com/zhyxun/Separating-Style-and-Content-for-Generalized-Style-Transfer/master/images/network.png) - results ![](https://raw.githubusercontent.com/zhyxun/Separating-Style-and-Content-for-Generalized-Style-Transfer/master/images/area2.png) ![](https://raw.githubusercontent.com/zhyxun/Separating-Style-and-Content-for-Generalized-Style-Transfer/master/images/area4.png) - **Deep Learning for Classical Japanese Literature** - [[paper]](https://arxiv.org/abs/1812.01718)[[GitHub]](https://github.com/rois-codh/kmnist) - Tarin Clanuwat, Mikel Bober-Irizar, Asanobu Kitamoto, Alex Lamb, Kazuaki Yamamoto, David Ha - NeurIPS 2018 - Kuzushiji-MNIST,Kuzushiji-49 and Kuzushiji-Kanji - Kuzushiji-MNIST ![](https://raw.githubusercontent.com/rois-codh/kmnist/master/images/kmnist_examples.png) - Kuzushiji-Kanji ![](https://raw.githubusercontent.com/rois-codh/kmnist/master/images/kkanji_examples.png) - **Multi-Content GAN for Few-Shot Font Style Transfer** - [[code]](https://github.com/azadis/MC-GAN)[[paper]](https://arxiv.org/abs/1712.00516)[[blog]](https://bair.berkeley.edu/blog/2018/03/13/mcgan/) - Azadi, Samaneh, Matthew Fisher, Vladimir Kim, Zhaowen Wang, Eli Shechtman, and Trevor Darrell. - CVPR2018 ![](https://bair.berkeley.edu/static/blog/mcgan/given-new-titles.jpg) ![](https://bair.berkeley.edu/static/blog/mcgan/ft51_1_fake_B.gif) - **Learning to Write Stylized Chinese Characters by Reading a Handful of Examples** - [[paper]](https://www.ijcai.org/proceedings/2018/0128.pdf) - Danyang Sun∗, Tongzheng Ren∗, Chongxuan Li, Hang Su†, Jun Zhu† - IJCAI 2018 - SA-VAE ![](https://i.imgur.com/9i5bFS0.png) - **DCFont: An End-To-End Deep Chinese Font Generation System** - [[paper]](http://www.icst.pku.edu.cn/zlian/docs/20181024110234919639.pdf) - Juncheng Liu, Zhouhui Lian, Jianguo Xiao - SIGGRAPH Asia 2017 ![](https://i.imgur.com/rQYFZRU.png) - **zi2zi: Master Chinese Calligraphy with Conditional Adversarial Networks** - [[blog]](https://kaonashi-tyc.github.io/2017/04/06/zi2zi.html) [[code(TensorFlow)]](https://github.com/kaonashi-tyc/zi2zi) [[code(pytorch)(xuan-li)]](https://github.com/xuan-li/zi2zi-pytorch) [[code(pytorch)( EuphoriaYan)]](https://github.com/EuphoriaYan/zi2zi-pytorch) - Yuchen Tian - 2017 ![](https://kaonashi-tyc.github.io/assets/intro.gif) - **Rewrite: Neural Style Transfer For Chinese Fonts** - [[code]](https://github.com/kaonashi-tyc/Rewrite) - Yuchen Tian - 2016 ![](https://raw.githubusercontent.com/kaonashi-tyc/Rewrite/master/images/single_font_progress.gif) - **Automatic generation of large-scale handwriting fonts via style learning** - [[paper]](https://dl.acm.org/citation.cfm?id=3005371) - Zhouhui Lian, Bo Zhao, and Jianguo Xiao - SIGGRAPH ASIA 2016 ![](https://ai2-s2-public.s3.amazonaws.com/figures/2017-08-08/a9c74b454bfaedceb0c06a3d82f133e4c9c0257e/3-Figure4-1.png) - **A Book from the Sky 天书: Exploring the Latent Space of Chinese Handwriting** - [[blog]](http://genekogan.com/works/a-book-from-the-sky/) - [Gene Kogan](http://genekogan.com/) ![](http://genekogan.com/images/a-book-from-the-sky/banner.png) - **Letter Spirit: An Emergent Model of the Perception and Creation of Alphabetic Style** - [[paper]](https://pdfs.semanticscholar.org/e03a/21a4dfaa34b3d43ab967a01d7d9f6f7adccf.pdf) - Douglas Hofstadter, Gary McGraw - 1993 ### Other Approach - **Automatic Generation of Typographic Font from a Small Font Subset** - [[paper]](https://arxiv.org/abs/1701.05703) - Tomo Miyazaki, Tatsunori Tsuchiya, Yoshihiro Sugaya, Shinichiro Omachi, Masakazu Iwamura, Seiichi Uchida, Koichi Kise - 2017 ![](https://pbs.twimg.com/media/C22YtOvWEAA8XsT.jpg) - **FlexyFont: Learning Transferring Rules for Flexible Typeface Synthesis** - [[paper]](https://doi.org/10.1111/cgf.12763) - H. Q. Phan, H. Fu, and A. B. Chan - 2015 Computer Graphics Forum ![](https://ai2-s2-public.s3.amazonaws.com/figures/2017-08-08/616f7c6bf71946430db5561cfa4045a022f29f7f/4-Figure4-1.png) - **Awesome Typography: Statistics-Based Text Effects Transfer** - [[paper]](https://arxiv.org/pdf/1611.09026.pdf)[[code]](https://github.com/williamyang1991/Text-Effects-Transfer) - Shuai Yang, Jiaying Liu, Zhouhui Lian and Zongming Guo - CVPR 2017 ![](https://pbs.twimg.com/media/CydToymWgAAbddo.jpg) - **Easy generation of personal Chinese handwritten fonts** - [[paper]](https://ieeexplore.ieee.org/document/6011892/) - Baoyao Zhou, Weihong Wang, and Zhanghui Chen - 2011 ICME(IEEE International Conference on Multimedia and Expo) ![](https://ai2-s2-public.s3.amazonaws.com/figures/2017-08-08/4760fce6c4ce72b17abe9595f1e635b6ecef70fc/3-Figure2-1.png) - **Automatic shape morphing for Chinese characters** - [[paper]](https://dl.acm.org/citation.cfm?id=2407748) - Zhouhui Lian, and Zhouhui Lian - SIGGRAPH Asia 2012 - ![](https://ai2-s2-public.s3.amazonaws.com/figures/2017-08-08/f4de25085605e82bd635666cd5676a7075e77520/2-Figure2-1.png) ## Struture Learning - **Analyzing 50k fonts using deep neural networks** - [[blog]](https://erikbern.com/2016/01/21/analyzing-50k-fonts-using-deep-neural-networks.html) - [Erik Bernhardsson](https://erikbern.com/about.html) - 2016 ![](https://erikbern.com/assets/animated_font.gif) - **Learning a Manifold of Fonts** - [[paper]](http://vecg.cs.ucl.ac.uk/Projects/projects_fonts/papers/siggraph14_learning_fonts.pdf)[[project(demo)]](http://vecg.cs.ucl.ac.uk/Projects/projects_fonts/projects_fonts.html) - Neill D.F. Campbell, and Jan Kautz - SIGGRAPH 2014 ![](http://vecg.cs.ucl.ac.uk/Projects/projects_fonts/images/projects/font_hamburgefon_large.png) ## DataSet - **Chinese Handwriting Recognition Competition 2013** - [[paper]](https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=3&ved=2ahUKEwipwtmZ3NXdAhUJyrwKHYBuAp4QFjACegQIAxAC&url=http%3A%2F%2Fblog.sciencenet.cn%2Fhome.php%3Fmod%3Dattachment%26id%3D48833&usg=AOvVaw3z6eOWVROK6CCdPly6Te5n)[[download]](http://www.nlpr.ia.ac.cn/databases/handwriting/Download.html) ![](https://i.imgur.com/jZcj4oo.png) - **Deep Learning for Classical Japanese Literature** - [[paper]](https://arxiv.org/abs/1812.01718)[[GitHub]](https://github.com/rois-codh/kmnist) - Tarin Clanuwat, Mikel Bober-Irizar, Asanobu Kitamoto, Alex Lamb, Kazuaki Yamamoto, David Ha - NeurIPS 2018 - Kuzushiji-MNIST,Kuzushiji-49 and Kuzushiji-Kanji - Kuzushiji-MNIST ![](https://raw.githubusercontent.com/rois-codh/kmnist/master/images/kmnist_examples.png) - Kuzushiji-Kanji ![](https://raw.githubusercontent.com/rois-codh/kmnist/master/images/kkanji_examples.png) ## Other Application - **FontCode: Embedding Information in Text Documents Using Glyph Perturbation** - [[paper]](http://www.cs.columbia.edu/cg/fontcode/fontcode.pdf)[[project page]](http://www.cs.columbia.edu/cg/fontcode/) - Chang Xiao, Cheng Zhang, Changxi Zheng - SIGGRAPH 2018 - <iframe width="560" height="315" src="https://www.youtube.com/embed/dejrBf9jW24" frameborder="0" allow="autoplay; encrypted-media" allowfullscreen></iframe>