collaborators

5 papers

eess.IV2026

FlowSteer: Conditioning Flow Field for Consistent Image Restoration

Tharindu Wickremasinghe, Chenyang Qi, Harshana Weligampola +2

Flow-based text-to-image (T2I) models excel at prompt-driven image generation, but falter on Image Restoration (IR), often "drifting away" from being faithful to the measurement. P…

cs.CV2026

SeeU: Seeing the Unseen World via 4D Dynamics-aware Generation

Yu Yuan, Tharindu Wickremasinghe, Zeeshan Nadir +3

Images and videos are discrete 2D projections of the 4D world (3D space + time). Most visual understanding, prediction, and generation operate directly on 2D observations, leading…

cs.CV2026

NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics

Yu Yuan, Xijun Wang, Tharindu Wickremasinghe +3

A primary bottleneck in large-scale text-to-video generation today is physical consistency and controllability. Despite recent advances, state-of-the-art models often produce unrea…

eess.IV2025

Affine Subspace Models and Clustering for Patch-Based Image Denoising

Tharindu Wickremasinghe, Marco F. Duarte

Image tile-based approaches are popular in many image processing applications such as denoising (e.g., non-local means). A key step in their use is grouping the images into cluster…

cs.IT2025

Max-Min Fairness for IRS-Assisted Secure Two-Way Communications

Harindu Jayarathne, Tharindu Wickremasinghe, Kasun T. Hemachandra +2

This paper investigates an intelligent reflective surface (IRS) assisted secure multi-user two-way communication system. The aim of this paper is to enhance the physical layer secu…