Krishna Srikar Durbha

I am a fourth-year Ph.D. student at Laboratory of Image and Video Engineering, The University of Texas at Austin, advised by Prof. Alan Bovik. As part of my research, I collaborate with Meta Video Infrastructure Team on Video Engineering and Perceptual Quality Optimization.

My research leverages self-supervised learning to bridge the gap between computational metrics and human-aligned visual perception. I specialize in developing robust, alignment-focused models for perceptual quality assessment, high-fidelity and high-resolution image generation, and the optimization of large-scale media delivery systems.

Google Scholar

GitHub

Resume

Education

Ph.D. in Electrical and Computer Engineering
2022 - 2026
The University of Texas at Austin
Advisor: Prof. Alan Bovik
Bachelor of Technology in Electrical Engineering
2018 - 2022
Indian Institute of Technology Hyderabad

Research Interests

Image and Video Representation Learning
Image and Video Processing
Generative AI
Perceptual Quality Assessment
Computer Vision
Video Streaming Optimization

News

01/2026: Passed my PhD Progress Review.
07/2025: My paper Constructing Per-Shot Bitrate Ladders Using Visual Information Fidelity has been accepted to the Journal, IEEE Transactions on Image Processing.
09/2025: Completed my PhD candidate evaluation.
07/2025: My paper Perceptual Classifiers: Detecting Generative Images using Perceptual Features has been accepted to the VQualA Workshop at ICCV 2025.
05/2025: I am excited to join the MPI team at Samsung Research America.
05/2024: I am excited to join the Wireless team at Skydio.
02/2024: My paper Bitrate Ladder Construction using Visual Information Fidelity was accepted at PCS 2024.
12/2023: Presented my work on Bitrate Ladder Construction at Video Quality Experts Group (VQEG) Meeting.

Research Ongoing | Under Review

	Unsupervised Image Quality Assessment Designing an Unsupervised Image Quality Assessment (IQA) model designed to decouple and identify complex visual degradations. [In Progress]
	High-Fidelity Image Generation using Self-Supervised Learning Developing a Representation Alignment framework to improve the visual fidelity and structural consistency of generative image models. [In Progress]
	Video Encoding Complexity A self-supervised learning approach to extract video representation features that are sensitive to encoding complexity of videos. [Under Review in ECCV 2026]
	Leveraging Compression to Construct Transferable Bitrate Ladders Krishna Srikar Durbha, Hassene Tmar, Ping-Hao Wu, Ioannis Katsavounidis and Alan C. Bovik [Paper] [Code] [Under Review in IEEE Transactions on Image Processing]

Published Papers

	Perceptual Classifiers: Detecting Generative Images using Perceptual Features K. S. Durbha, A. K. Venkataramanan, R. Sureddi, and A. C. Bovik. "Perceptual Classifiers: Detecting Generative Images using Perceptual Features." in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 3372-3382. 2025. [Paper] [Code]
	Constructing Per-Shot Bitrate Ladders using Visual Information Fidelity K. S. Durbha and A. C. Bovik, "Constructing Per-Shot Bitrate Ladders Using Visual Information Fidelity," in IEEE Transactions on Image Processing, vol. 34, pp. 7093-7108, 2025 [Paper] [Code]
	Bitrate Ladder Construction Using Visual Information Fidelity K. S. Durbha, H. Tmar, C. Stejerean, I. Katsavounidis and A. C. Bovik, "Bitrate Ladder Construction Using Visual Information Fidelity," 2024 Picture Coding Symposium (PCS), Taichung, Taiwan, 2024, pp. 1-4. [Paper] [Code]
	AutoML Models for Wireless Signals Classification and their effectiveness against Adversarial Attacks K. S. Durbha and S. Amuru, "AutoML Models for Wireless Signals Classification and their effectiveness against Adversarial Attacks," 2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS), 2022, pp. 265-269. [Paper] [Code]

Source Code Credit to Dr. Jon Barron