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…

eess.IV2026

Direct Kernel Optimization: Efficient Design for Opto-Electronic Convolutional Neural Networks

Ali Almuallem, Harshana Weligampola, Abhiram Gnanasambandam +5

Hybrid opto-electronic neural networks combine optical front-ends with electronic back-ends to perform vision tasks, but joint end-to-end (E2E) optimization of optical and electron…

eess.IV2025

Diffusion Algorithm for Metalens Optical Aberration Correction

Harshana Weligampola, Yuanrui Chen, Weiheng Tang +2

Metalenses offer a path toward creating ultra-thin optical systems, but they inherently suffer from severe, spatially varying optical aberrations, especially chromatic aberration,…

stat.ML2025

Continuous Semi-Implicit Models

Longlin Yu, Jiajun Zha, Tong Yang +4

Semi-implicit distributions have shown great promise in variational inference and generative modeling. Hierarchical semi-implicit models, which stack multiple semi-implicit layers,…

cs.LG2025

Tutorial on Diffusion Models for Imaging and Vision

Stanley H. Chan

The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying princip…