Richard Zhang

Research Scientist
Adobe Research
San Francisco, CA

rizhang at
[GitHub] [Google Scholar]
[Resume/CV] [Twitter] [Bio]

My research interests are in computer vision, machine learning, deep learning, graphics, and image processing. I obtained a PhD at UC Berkeley, advised by Prof. Alexei (Alyosha) Efros. I obtained BS and MEng degrees from Cornell University in ECE. I often collaborate with academic researchers, either through internships or university collaboration.


[Apr 2021] Our work on using generative models to improve discriminative models was accepted to CVPR.
[Apr 2021] Our work on few-shot GAN training was accepted to CVPR.
[Mar 2021] Our works on speeding up unconditional GANs for image editing and projection (AnyCost GANs) and conditional GANs with implicit functions (ASAPnet) were accepted to CVPR.
[Mar 2021] Our work on audio perceptual metrics was accepted to ICASSP.
[Sept 2020] Few updates regarding Antialiasing CNNs [ICML 2019], which can stabilize and improve the backbone for your application:
- Easy installation: pip install antialiased-cnns and import antialiased_cnns; model = antialiased_cnns.resnet50(pretrained= True)
- For more information, including "What is Aliasing?", see my guest lecture [15 min] in SFU CMPT 361, Intro to Vision, Sampling and Aliasing lecture.
- A nice followup work, Delving Deeper into Antialiasing in Convnets by Zou, Xiao, Yu, & Lee, won best paper at BMVC 2020. Check it out!
[Aug 2020] I gave a talk on Detecting Generated Imagery, Deep and Shallow (35 min) at the Sensing Humans workshop at ECCV.
[Aug 2020] I gave a talk on Style and Structure Disentanglement for Image Manipulation (30 min) at the Advances in Image Manipulation workshop at ECCV.
[Aug 2020] I gave a talk on Analyzing Artifacts in Discriminative and Generative Models (40 min) at the GAMES webinar.
[July 2020] Our work on using contrastive learning for unpaired translation was accepted to ECCV.
[July 2020] Our work on inverting GANs was accepted to ECCV as an oral.
[July 2020] See our new work on Swapping Autoencoders below.
[July 2020] Our work on audio perceptual metrics was accepted to Intespeech.


  Ensembling with Deep Generative Views
Lucy Chai, Jun-Yan Zhu, Eli Shechtman, Phillip Isola, Richard Zhang
To appear in CVPR, 2021.
[Paper] [Webpage] [GitHub] [Colab] [Bibtex]
  Few-shot Image Generation via Cross-domain Correspondence
Utkarsh Ojha, Yijun Li, Jingwan Lu, Alexei A. Efros, Yong Jae Lee, Eli Shechtman, Richard Zhang
To appear in CVPR, 2021.
[Paper] [Webpage] [GitHub] [Bibtex]
  Anycost GANs for Interactive Image Synthesis and Editing
Ji Lin, Richard Zhang, Frieder Ganz, Song Han, Jun-Yan Zhu
To appear in CVPR, 2021.
[Paper] [Webpage] [Video] [GitHub] [Bibtex]
  Spatially-Adaptive Pixelwise Networks for Fast Image Translation
Tamar Rott Shaham, Michaël Gharbi, Richard Zhang, Eli Shechtman, Tomer Michaeli
To appear in CVPR, 2021.
[Paper] [Webpage] [Bibtex]
  Editing Conditional Radiance Fields
Steven Liu, Xiuming Zhang, Zhoutong Zhang, Richard Zhang, Jun-Yan Zhu, Bryan Russell
In ArXiv, 2021.
[Paper] [Webpage] [GitHub] [Video] [Demo] [Bibtex]
  On Buggy Resizing Libraries and Surprising Subtleties in FID Calculation
Gaurav Parmar, Richard Zhang, Jun-Yan Zhu
In ArXiv, 2021.
[Paper] [Webpage] [GitHub] [Bibtex]
CDPAM: Contrastive Learning for Perceptual Audio Similarity
Pranay Manocha, Zeyu Jin, Richard Zhang, Adam Finkelstein
To appear in ICASSP, 2021.
[Paper] [Webpage] [GitHub] [Bibtex]
  The Low-Rank Simplicity Bias in Deep Networks
Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung, Pulkit Agrawal, Phillip Isola
In ArXiv, 2021.
[Paper] [Webpage] [GitHub] [Bibtex]
    Swapping Autoencoder for Deep Image Manipulation
Taesung Park, Jun-Yan Zhu, Oliver Wang, Jingwan Lu, Eli Shechtman, Alexei A. Efros, Richard Zhang
In NeurIPS, 2020.
[Paper] [Webpage] [GitHub] [Video] [Bibtex]
  Few-shot Image Generation with Elastic Weight Consolidation
Yijun Li, Richard Zhang, Jingwan Lu, Eli Shechtman
In NeurIPS, 2020.
[Paper] [Supplemental] [Webpage] [Bibtex]
  Contrastive Learning for Unpaired Image-to-Image Translation
Taesung Park, Alexei A. Efros, Richard Zhang, Jun-Yan Zhu
In ECCV, 2020.
[Paper] [Webpage] [GitHub] [Teaser] [Video] [Bibtex]
Transforming and Projecting Images into Class-conditional Generative Networks
Minyoung Huh, Richard Zhang, Jun-Yan Zhu, Sylvain Paris, Aaron Hertzmann
In ECCV (oral), 2020.
[Paper] [Webpage] [GitHub] [Bibtex]
A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences
Pranay Manocha, Adam Finkelstein, Richard Zhang, Nicholas J. Bryan, Gautham J. Mysore, Zeyu Jin
In Interspeech, 2020.
[Paper] [Webpage] [GitHub] [Bibtex]
CNN-generated images are surprisingly easy to spot...for now
Sheng-Yu Wang, Oliver Wang, Richard Zhang, Andrew Owens, Alexei A. Efros
In CVPR, 2020 (oral).
[Paper] [Webpage] [GitHub] [Talk] [Bibtex]
Deep Parametric Shape Predictions using Distance Fields
Dmitriy Smirnov, Matthew Fisher, Vladimir G. Kim, Richard Zhang, Justin Solomon
In CVPR, 2020.
[Paper] [Webpage] [GitHub] [Video] [Bibtex]
Image Morphing with Perceptual Constraints and STN Alignment
Noa Fish, Richard Zhang, Lilach Perry, Daniel Cohen-Or, Eli Shechtman, Connelly Barnes
In CGF, 2020.
[Paper] [GitHub] [Bibtex]
Making Convolutional Networks Shift-Invariant Again
Richard Zhang
In ICML, 2019.
[Paper] [Webpage] [GitHub] [Talk] [Slides (129mb)] [Poster] [Bibtex]
Detecting Photoshopped Faces by Scripting Photoshop
Sheng-Yu Wang, Oliver Wang, Andrew Owens, Richard Zhang, Alexei A. Efros
In ICCV, 2019.
[Paper] [Webpage] [GitHub] [Video] [Poster] [Adobe Max] [Adobe Blog] [Bibtex]
Interactive Sketch & Fill: Multiclass Sketch-to-Image Translation
Arnab Ghosh, Richard Zhang, Puneet Dokania, Oliver Wang, Alexei A. Efros, Philip H.S. Torr, Eli Shechtman In ICCV, 2019.
[Paper] [Webpage] [GitHub] [Video] [Bibtex]
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
Richard Zhang, Phillip Isola, Alexei A. Efros, Eli Shechtman, Oliver Wang
In CVPR, 2018.
[Paper] [Webpage] [GitHub] [Poster] [Adobe Blog] [Two Min Papers] [Bibtex]
Stochastic Adversarial Video Prediction
Alex X. Lee, Richard Zhang, Frederik Ebert, Pieter Abbeel, Chelsea Finn, Sergey Levine
In ArXiv, 2018.
[Paper] [Webpage] [GitHub] [Bibtex]
Toward Multimodal Image-to-Image Translation
Jun-Yan Zhu, Richard Zhang, Deepak Pathak, Trevor Darrell, Alexei A. Efros, Oliver Wang, Eli Shechtman
In NIPS, 2017.
[Paper] [Webpage] [GitHub] [Video (YouTube)(mp4)] [Poster] [Two Min Papers] [Bibtex]
Real-Time User-Guided Image Colorization with Learned Deep Priors
Richard Zhang*, Jun-Yan Zhu*, Phillip Isola, Xinyang Geng, Angela S. Lin, Tianhe Yu, Alexei A. Efros
(*indicates equal contribution)
In SIGGRAPH, 2017.
[Paper] [Webpage] [Fastforward] [Talk] [Video (YouTube)(mp4)] [PSE 2020] [GitHub] [Slides (141mb)] [Bibtex]
Split-Brain Autoencoders: Unsupervised Learning by Cross-Channel Prediction
Richard Zhang, Phillip Isola, Alexei A. Efros
In CVPR, 2017.
[Paper] [Webpage] [GitHub] [Poster] [Seminar Talk] [Bibtex]
Colorful Image Colorization
Richard Zhang, Phillip Isola, Alexei A. Efros
In ECCV, 2016 (oral).
[Paper] [Webpage] [GitHub] [Talk] [Slides (138mb)] [Poster] [Bibtex]
Sensor Fusion for Semantic Segmentation of Urban Scenes
Richard Zhang, Stefan Candra, Kai Vetter, Avideh Zakhor
In ICRA, 2015.
[Paper (pdf)(official)] [Slides] [Poster] [Talk] [Annotations (tar)(zip) ] [Bibtex]
Automatic Identification of Window Regions on Indoor Point Clouds Using LiDAR and Cameras
Richard Zhang, Avideh Zakhor
In WACV, 2014.
[Paper (pdf)(official)] [Bibtex]


Image Synthesis for Self-Supervised Visual Representation Learning
Richard Zhang
Spring 2018.
[Thesis] [Dissertation Talk] [Fast Forward] [Slides (396 MB)] [Bibtex]


Reviewer recognitions, CVPR 2019, NeurIPS 2019, ECCV 2020, NeurIPS 2020
Thesis Fast Forward, Best Presentation, SIGGRAPH 2018
Adobe Research Fellowship 2017

Student collaborators/interns

I have gotten to work with some wonderful collaborators.

PhD [interns]
Lucy Chai, MIT (Fellowship winner, 2021)
Taesung Park, UC Berkeley (Fellowship winner, 2020)
Ji Lin, MIT
William (Bill) Peebles, UC Berkeley
Alex Andonian, MIT
Utkarsh Ojha, UC Davis
Arnab Ghosh, Oxford
Minyoung (Jacob) Huh, MIT
Tamar Rott Shaham, Technion (Fellowship winner, 2020)
Peiye Zhuang, UIUC
Dima Smirnov, MIT
Noa Fish, Tel Aviv

Masters/Undergrad [interns]
Steven Liu, MIT
Seungjoo Yoo, Korea Univ (WIT scholarship winner, 2019)

PhD [university collaborators]
Pranay Manocha, Princeton
Rawan Alghofaili, George Mason
Alvin Wan, UC Berkeley

Undergrad [university collaborators]
Sheng-Yu Wang, UC Berkeley
Xin Qin, now @ USC
Hemang Jangle
Angela S. Lin, now @ UT Austin
Xinyang Geng, now @ UC Berkeley
Tianhe Yu, now @ Stanford
Stefan A. Candra


Introduction to Artificial Intelligence (CS 188), UC Berkeley
Graduate Student Instructor (GSI) with Prof. Anca Dragan
Spring 2017

Computer Vision (CS 280), UC Berkeley
Graduate Student Instructor (GSI) with Prof. Alexei A. Efros, Prof. Trevor Darrell
Spring 2016

Introduction to Circuits (ECE 2100), Cornell University
Teaching Assistant (TA) with Prof. Alyosha Molnar
Spring 2010

My Name

Confused by the contents of this page? Well, you may have been looking for Professor Richard Zhang or Professor Richard Zhang. My Chinese name is 章睿嘉.