Search

Your search keyword '"Kim, Sumin"' showing total 1,663 results
Start Over Author "Kim, Sumin"
1,663 results on '"Kim, Sumin"'

1. Segment Anything in Medical Images and Videos: Benchmark and Deployment

Author

Ma, Jun, Kim, Sumin, Li, Feifei, Baharoon, Mohammed, Asakereh, Reza, Lyu, Hongwei, and Wang, Bo

Subjects
Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition
Abstract

Recent advances in segmentation foundation models have enabled accurate and efficient segmentation across a wide range of natural images and videos, but their utility to medical data remains unclear. In this work, we first present a comprehensive benchmarking of the Segment Anything Model 2 (SAM2) across 11 medical image modalities and videos and point out its strengths and weaknesses by comparing it to SAM1 and MedSAM. Then, we develop a transfer learning pipeline and demonstrate SAM2 can be quickly adapted to medical domain by fine-tuning. Furthermore, we implement SAM2 as a 3D slicer plugin and Gradio API for efficient 3D image and video segmentation. The code has been made publicly available at \url{https://github.com/bowang-lab/MedSAM}.

Published
2024

2. SPnet: Estimating Garment Sewing Patterns from a Single Image

Author

Lim, Seungchan, Kim, Sumin, and Lee, Sung-Hee

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence
Abstract

This paper presents a novel method for reconstructing 3D garment models from a single image of a posed user. Previous studies that have primarily focused on accurately reconstructing garment geometries to match the input garment image may often result in unnatural-looking garments when deformed for new poses. To overcome this limitation, our approach takes a different approach by inferring the fundamental shape of the garment through sewing patterns from a single image, rather than directly reconstructing 3D garments. Our method consists of two stages. Firstly, given a single image of a posed user, it predicts the garment image worn on a T-pose, representing the baseline form of the garment. Then, it estimates the sewing pattern parameters based on the T-pose garment image. By simulating the stitching and draping of the sewing pattern using physics simulation, we can generate 3D garments that can adaptively deform to arbitrary poses. The effectiveness of our method is validated through ablation studies on the major components and a comparison with other approaches.

Published
2023

18. A lateral resolution metric for static single molecule localization microscopy images from time-resolved pair correlation functions

Author

Shaw, Thomas R., Fazekas, Frank J., Kim, Sumin, Flanagan-Natoli, Jennifer C., Sumrall, Emily R., and Veatch, Sarah L.

Subjects
Physics - Biological Physics
Abstract

Single molecule localization microscopy (SMLM) permits the visualization of cellular structures an order of magnitude smaller than the diffraction limit of visible light, and an accurate, objective evaluation of the resolution of an SMLM dataset is an essential aspect of the image processing and analysis pipeline. Here we present a simple method that uses the pair autocorrelation function evaluated both in space and time to measure the time-interval dependent point-spread function of SMLM images of static samples. Using this approach, we demonstrate that experimentally obtained images typically have effective point spread functions that are broader than expected from the localization precision alone, due to additional uncertainty arising from drift and drift correction algorithms. This resolution metric reports on how precisely one can measure pairwise distances between labeled objects and is complementary to the commonly used Fourier Ring Correlation metric that also considers spatial sampling. The method is demonstrated on simulated localizations, DNA origami rulers, and cellular structures labelled by dye-conjugated antibodies or fluorescent fusion proteins., Comment: 29 pages, 13 figures (including supplement)

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results