Search Results for author: Malsha V. Perera

Found 7 papers, 3 papers with code

Frame by Familiar Frame: Understanding Replication in Video Diffusion Models

no code implementations28 Mar 2024 Aimon Rahman, Malsha V. Perera, Vishal M. Patel

In our paper, we present a systematic investigation into the phenomenon of sample replication in video diffusion models.

Image Generation Video Generation

Analyzing Bias in Diffusion-based Face Generation Models

no code implementations10 May 2023 Malsha V. Perera, Vishal M. Patel

Diffusion models are becoming increasingly popular in synthetic data generation and image editing applications.

Attribute Face Generation +2

SAR Despeckling using a Denoising Diffusion Probabilistic Model

1 code implementation9 Jun 2022 Malsha V. Perera, Nithin Gopalakrishnan Nair, Wele Gedara Chaminda Bandara, Vishal M. Patel

The despeckled image is recovered by a reverse process which iteratively predicts the added noise using a noise predictor which is conditioned on the speckled image.

Change Detection Denoising

SAR Despeckling Using Overcomplete Convolutional Networks

1 code implementation31 May 2022 Malsha V. Perera, Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Vishal M. Patel

We show that the proposed network improves despeckling performance compared to recent despeckling methods on synthetic and real SAR images.

Transformer-based SAR Image Despeckling

1 code implementation23 Jan 2022 Malsha V. Perera, Wele Gedara Chaminda Bandara, Jeya Maria Jose Valanarasu, Vishal M. Patel

Synthetic Aperture Radar (SAR) images are usually degraded by a multiplicative noise known as speckle which makes processing and interpretation of SAR images difficult.

Sar Image Despeckling

A Thickness Sensitive Vessel Extraction Framework for Retinal and Conjunctival Vascular Tortuosity Analysis

no code implementations2 Jan 2021 Ashwin De Silva, Malsha V. Perera, Navodini Wijethilake, Saroj Jayasinghe, Nuwan D. Nanayakkara, Anjula De Silva

In addition, the proposed framework was utilized to determine the association of diabetes with retinal and conjunctival vascular tortuosity.

A Joint Convolutional and Spatial Quad-Directional LSTM Network for Phase Unwrapping

no code implementations26 Oct 2020 Malsha V. Perera, Ashwin De Silva

Phase unwrapping is a classical ill-posed problem which aims to recover the true phase from wrapped phase.

Cannot find the paper you are looking for? You can Submit a new open access paper.