Krishna Kumar Singh

Senior Research Scientist and Manager
Adobe Research
Email: krishsin[at]adobe.com

I am a senior research scientist and manager at Adobe Research. My research focuses on developing generative model for image generation and editing. Recently, I have been focusing on generating and editing complex scenes and objects. I am also working on image editing models for inpainting and outpaitning tasks which is currently used as Generative Fill in Photoshop and Firefly.

I got Phd in Computer Science from University of California, Davis under guidance of Prof. Yong Jae Lee. Previously, I finished my Masters in Robotics at Carnegie Mellon University, advised by Prof. Alexei Efros and Prof. Kayvon Fatahalian. I did undergrad in Computer Science and Engineering at IIIT Hyderabad under supervision of Prof. P J Narayanan.

I was research intern at Intel Labs and was Carnegie Mellon’s Robotics Institute Summer Scholar (RISS) under Prof. Martial Hebert. I also interned at Allen Institute for Artificial Intelligence (AI2) with Dr. Santosh Divvala and Prof. Ali Farhadi. I was a research intern at Facebook AI this summer and worked with Dr. Deepti Ghadiyaram, Dr. Dhruv Mahajan , Dr. Matt Feiszli, and Prof. Kristen Grauman.

Resume/Linkedin/Google-Scholar

Internship: If you are interested in doing research project with me at Adobe, please send me an email with your resume.

Product / Industry

Generative Fill and Expand
in Photoshop and Firefly
Core researcher for modeling of Generative Fill and Expand
Awarded by TIME as one of best inventions of 2023

Skin Smoothing Neural Filter
in Photoshop

Strike a Pose
Adobe Max Sneaks, 2021

Papers

ActAnywhere: Subject-Aware Video Background Generation
Boxiao Pan, Zhan Xu, Chun-Hao Paul Huang, Krishna Kumar Singh, Yang Zhou, Leonidas J. Guibas, Jimei Yang
Conference on Neural Information Processing Systems (NeurIPS), 2024

Generative Portrait Shadow Removal
Jae Shin Yoon, Zhixin Shu, Mengwei Ren, Xuaner Zhang, Yannick Hold-Geoffroy, Krishna Kumar Singh, He Zhang
ACM Transactions on Graphics (SIGGRAPH) Asia, 2024

Removing Distributional Discrepancies in Captions Improves Image-Text Alignment
Yuheng Li, Haotian Liu, Mu Cai, Yijun Li, Eli Shechtman, Zhe Lin, Yong Jae Lee, and Krishna Kumar Singh
European Conference on Computer Vision (ECCV), 2024

GroupDiff: Diffusion-based Group Portrait Editing
Yuming Jiang, Nanxuan Zhao, Qing Liu, Krishna Kumar Singh, Shuai Yang, Chen Change Loy, Ziwei Liu
European Conference on Computer Vision (ECCV), 2024

Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods
Wonwoong Cho, Hareesh Ravi, Midhun Harikumar, Vinh Khuc, Krishna Kumar Singh, Jingwan Lu, David I Inouye, Ajinkya Kale
European Conference on Computer Vision (ECCV), 2024

Separate-and-Enhance: Compositional Finetuning for Text-to-Image Diffusion Models
Zhipeng Bao, Yijun Li, Krishna Kumar Singh, Yu-Xiong Wang, Martial Hebert
ACM Transactions on Graphics (SIGGRAPH), 2024

UniHuman: A Unified Model for Editing Human Images in the Wild
Nannan Li, Qing Liu, Krishna Kumar Singh, Yilin Wang, Jianming Zhang, Bryan A. Plummer, Zhe Lin
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024

P2D: Plug and Play Discriminator for accelerating GAN frameworks
Min Jin Chong, Krishna Kumar Singh,Yijun Li, Jingwan Lu, David Forsyth
Winter Conference on Applications of Computer Vision (WACV), 2024

Discovering and Mitigating Biases in CLIP-based Image Editing
Md Mehrab Tanjim, Krishna Kumar Singh, Kushal Kafle, Ritwik Sinha, Garrison W. Cottrell
Winter Conference on Applications of Computer Vision (WACV), 2024

Consistent Multimodal Generation via A Unified GAN Framework
Zhen Zhu, Yijun Li, Weijie Lyu, Krishna Kumar Singh , Zhixin Shu, Sören Pirk, Derek Hoiem
Winter Conference on Applications of Computer Vision (WACV), 2024

UMFuse: Unified Multi View Fusion for Human Editing applications
Rishabh Jain, Mayur Hemani, Duygu Ceylan, Krishna Kumar Singh, Jingwan Lu, Mausoom Sarkar, Balaji Krishnamurthy
Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2023

Zero-shot Image-to-Image Translation
Gaurav Parmar, Krishna Kumar Singh, Richard Zhang, Yijun Li, Jingwan Lu, Jun-Yan Zhu
ACM Transactions on Graphics (SIGGRAPH), 2023

Modulating Pretrained Diffusion Models for Multimodal Image Synthesis
Cusuh Ham, James Hays, Jingwan Lu, Krishna Kumar Singh, Zhifei Zhang, Tobias Hinz
ACM Transactions on Graphics (SIGGRAPH), 2023

Putting People in Their Place: Affordance-Aware Human Insertion into Scenes
Sumith Kulal, Tim Brooks, Alex Aiken, Jiajun Wu, Jimei Yang, Jingwan Lu, Alexei A Efros, Krishna Kumar Singh
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

VGFlow: Visibility guided Flow Network for Human Reposing
Rishabh Jain, Krishna Kumar Singh, Mayur Hemani, Jingwan Lu, Mausoom Sarkar, Duygu Ceylan, Balaji Krishnamurthy
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Complete 3D Human Reconstruction from a Single Incomplete Image
Junying Wang, Jae Shin Yoon, Tuanfeng Y. Wang, Krishna Kumar Singh, and Ulrich Neumann
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Debiasing Image-to-Image Translation Models
Md Mehrab Tanjim, Krishna Kumar Singh, Kushal Kafle, Ritwik Sinha, Garrison W. Cottrell
British Machine Vision Conference (BMVC), 2022

Contrastive Learning for Diverse Disentangled Foreground Generation
Yuheng Li, Yijun Li, Jingwan Lu, Eli Shechtman, Yong Jae Lee, Krishna Kumar Singh
European Conference on Computer Vision (ECCV) , 2022

Discovering and Mitigating Biases in CLIP-based Text-to-Image Generation
Md Mehrab Tanjim, Krishna Kumar Singh, Kushal Kafle, Ritwik Sinha, Garrison W. Cottrell
European Conference on Computer Vision (ECCV) Worshop, 2022

Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing
Gaurav Parmar, Yijun Li, Jingwan Lu, Richard Zhang, Jun-Yan Zhu, Krishna Kumar Singh
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022

GIRAFFE HD: A High-Resolution 3D-aware Generative Model
Yang Xue, Yuheng Li, Krishna Kumar Singh , Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022

InsetGAN for Full-Body Image Generation
Anna Frühstück, Krishna Kumar Singh, Eli Shechtman, Niloy J. Mitra, Peter Wonka, Jingwan Lu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Generating and Controlling Diversity in Image Search
Md Mehrab Tanjim, Ritwik Sinha, Krishna Kumar Singh , Sridhar Mahadevan, David Arbour, Moumita Sinha, Garrison W. Cottrell
Winter Conference on Applications of Computer Vision (WACV), 2022

Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis
Tuanfeng Y. Wang, Duygu Ceylan, Krishna Kumar Singh, Niloy J. Mitra
International Conference on 3D Vision (3DV), 2021
(oral presentation)

PartGAN: Weakly-supervised Part Decomposition for Image Generation and Segmentation
Yuheng Li, Krishna Kumar Singh , Yang Xue, Yong Jae Lee
British Machine Vision Conference (BMVC), 2021

Collaging Class-specific GANs for Semantic Image Synthesis
Yuheng Li, Yijun Li, Jingwan Lu, Eli Shechtman, Yong Jae Lee, Krishna Kumar Singh
Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2021

Seeing the Unseen: Predicting the First-Person Camera Wearer's Location and Pose in Third-Person Scenes
Yangming Wen, Krishna Kumar Singh, Markham Anderson, Wei-Pang Jan, Yong Jae Lee
International Workshop on Egocentric Perception, Interaction and Computing (EPIC), ICCV 2021

IMAGINE: Image Synthesis by Image-Guided Model Inversion
Pei Wang, Yijun Li, Krishna Kumar Singh, Jingwan Lu, Nuno Vasconcelos
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Generating Furry Cars: Disentangling Object Shape and Appearance across Multiple Domains
Utkarsh Ojha, Krishna Kumar Singh, Yong Jae Lee
International Conference on Learning Representations (ICLR), 2021

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
Utkarsh Ojha, Krishna Kumar Singh, Cho-Jui Hsieh, Yong Jae Lee
Conference on Neural Information Processing Systems (NeurIPS), 2020

Don’t Judge an Object by Its Context: Learning to Overcome Contextual Bias
Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Oral Presentation

MixNMatch: Multifactor Disentanglement and Encoding for Conditional Image Generation
Yuheng Li, Krishna Kumar Singh, Utkarsh Ojha, Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020

FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
Krishna Kumar Singh*, Utkarsh Ojha*, Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019
* equal contribution
Oral Presentation

You reap what you sow: Using Videos to Generate High Precision Object Proposals for Weakly-supervised Object Detection
Krishna Kumar Singh, Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019

DOCK: Detecting Objects by transferring Common-sense Knowledge
Krishna Kumar Singh, Santosh Divvala, Ali Farhadi, Yong Jae Lee
European Conference on Computer Vision (ECCV), 2018

Who Will Share My Image? Predicting the Content Diffusion Path in Online Social Networks
Wenjian Hu, Krishna Kumar Singh*, Fanyi Xiao*, Jinyoung Han, Chen-Nee Chuah, Yong Jae Lee
ACM International Conference on Web Search and Data Mining (WSDM), 2018
* equal contribution

Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization
Krishna Kumar Singh, Yong Jae Lee
International Conference on Computer Vision (ICCV), 2017

Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond
Krishna Kumar Singh, Hao Yu, Aron Sarmasi, Gautam Pradeep, Yong Jae Lee
Arxiv, 2018

Identifying First-Person Camera Wearers in Third-Person Videos
C. Fan, J. Lee, M. Xu, K. K. Singh , Y. J. Lee, D. J. Crandall, and M. S. Ryoo
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

End-to-End Localization and Ranking for Relative Attributes
Krishna Kumar Singh, Yong Jae Lee
European Conference on Computer Vision (ECCV), 2016

Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection
Krishna Kumar Singh, Fanyi Xiao, Yong Jae Lee
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

KrishnaCam: Using a Longitudinal, Single-Person, Egocentric Dataset for Scene Understanding Tasks
Krishna Kumar Singh, Kayvon Fatahalian, Alexei A. Efros
Winter Conference on Applications of Computer Vision (WACV), 2016

Storytelling Patches: Predicting Tourist Spots in a City
Aayush Bansal, Krishna Kumar Singh
ECCV Workshop on Storytelling with Images and Videos (VisStory), 2014

Geometry Directed Browser for Personal Photographs
Aditya Deshpande, Siddharth Choudhary, P J Narayanan, Krishna Kumar Singh, Kaustav Kundu, Aditya Singh, Apurva Kumar
ACM Indian Conference On Vision, Graphics And Image Processing (ICVGIP), 2012 (oral presentation)
[Video]

Hybrid Multi-Core Algorithms for Regular Image Filtering Applications
Shrenik Lad, Krishna Kumar Singh, Kishore Kothapalli, P J Narayanan
IEEE International Conference on High Performance Computing (HiPC) Student Research Symposium, 2012 (NVIDIA Best GPU Poster Award) [Poster]

Present/Past Interns

Work Experience


Research Scientist and Manager at Adobe Research

Research Intern at Facebook AI (Summer 2019)
Worked on removing contextual bias in visual recognition.

Research Intern at Allen Institute for Artificial Intelligence (Summer 2017)
Worked on improving object detection by transferring common-sense knowledge.
Computer Vision Intern at Intel Labs (Summer 2015)
Worked on Video Summarization and Retrieval. Filed two patents.

Carnegie Mellon’s Robotics Institute Summer Scholar (RISS) under Prof. Martial Hebert (Summer 2012)
Worked on Object Recognition in Different Illumination Conditions. [Poster]