Krishnakant Singh

I am a PhD student at Visual Inference Lab at TU Darmstadt with Prof. Stefan Roth , where I work on computer vision and machine learning.

I am interested in generative modeling with a particular focus on compositionality and disentanglement of scenes. I previously spent three beautiful years at Rakuten research working on object detection, retrieval, and complementary item recommendation for fashion images. I completed my graduation from IIT Hyderabad , where I was advised by Vineeth N Balasubramanian .

Email  /  Bio  /  Résumé  /  Google Scholar  /  Twitter  /  Github

profile photo

Research

I'm interested in computer vision, machine learning, optimization, and image processing. Much of my research is focused on generative modeling with a focus on compositionality and disentanglement for images.





News

Apr' 25 😄 Excited to announce that I will be interning at Adobe Research for the summer of 2025.
Mar' 25 🚀 An updated version of our paper GLASS is accepted at CVPR 2025.
Sep' 24 🎉 Honoured to receive the outstanding reviewer award at ECCV 2024.
Jun' 24 🎉 Our paper won the best paper award @ CVPR 2024 Workshop: SyntaGen.
Apr' 24 📢 Selected for summer internship at Valeo.ai . Unfortunately, I had to turn it down due to visa issues.

Publications

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning
Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth,
CVPR 2025
Code (Coming Soon!) / arXiv
Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images
Krishnakant Singh, Thanush Navaratnam, Jannik Holmer Simone Schaub-Meyer, Stefan Roth,
CVPR 2024 Workshop: SyntaGen-Harnessing Generative Models for Synthetic Visual Datasets 2024 , Best Paper Award Winner
Code / arXiv
S2-Flow: Joint Semantic and Style Editing of Facial Images
Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth,
BMVC, 2022
Code / video / arXiv
Submodular Batch Selection for Training Deep Neural Networks
K J Joseph, Vamshi Teja Racha, Krishnakant Singh, Vineeth N. Balasubramanian,
IJCAI, 2019 and ICML Workshop, 2019
Code / arXiv / Video
Submodular Importance Sampling for training Neural Networks
Krishnakant Singh
Masters's Thesis
Code / arXiv

Work Experience

rit_logo Rakuten Research Research Scientist Jan, 2020 - March, 2021
rakuten_logo Rakuten Inc. Research Engineer Oct, 2018 - Jan, 2020
gsoc_logo Google Summer of Code with MLPack Summer Intern May - Sep 2017

Miscellanea

Reviewer: ICCV 2025, CVPR 2025, ECCV 2024, ICCV 2023, IJCAI 2018

Graduate Student Instructor at TU Darmstadt: Computer Vision-1 (WS 2021), Computer Vision-2 (SS22, SS23, SS24, SS25)

Graduate Student Instructor at IIT Hyderabad: Computer Vision-1 (WS 2021), Optimization Methods in Machine Learning (CS2630 Fall 2017), Deep Learning (CS5480 Spr 2018)


Website Credits to Mr. Jon Barron source code