HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Mon, 29 Jan 2024 15:51:47 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"65b7c993-4747"
expires: Tue, 30 Dec 2025 03:46:44 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 6C83:21D6A4:99C672:ACA0BC:695348CB
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 03:36:44 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210082-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767065804.951860,VS0,VE201
vary: Accept-Encoding
x-fastly-request-id: 9805b6b203d8ed0fb9cd0f75fbfd8405927649e5
content-length: 5111
Isaac Kasahara Samsung AI NYC
U of Minnesota
I am currently a Research Engineer at Samsung AI Center NYC, where I have the privilege of contributing to innovative advancements in the field. I am proud to have multiple publications in prestigious AI conferences such as ECCV, ICRA, and IROS. I hold a Master’s degree in Robotics from the University of Minnesota, which has equipped me with a strong understanding in computer vision and robotics.
My deep enthusiasm lies in the future of AI and robotics, as I am constantly inspired by the potential they hold. I hope to continue to explore new possibilities and pioneer novel methodologies, aiming to make notable contributions to these fields.
Jan 29, 2024 Paper accepted to ICRA 2024 Apr 28, 2023 Converted to full time Research Engineer at Samsung AI Center NYC Oct 27, 2022 Presented paper (poster & oral) at ECCV 2022 Aug 7, 2022 Started as a Research Intern at Samsung AI NYC May 22, 2022 Graduated from UMN with a Master’s in Robotics
2024 FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection
Hongsuk Choi, Isaac Kasahara , Selim Engin, and 3 more authors
2024
Text and pose embeddings can be composed using attention masks during the diffusion process to achieve instance-level control when generating images.
2023 Real-time Simultaneous Multi-Object 3D Shape Reconstruction, 6DoF Pose Estimation and Dense Grasp Prediction
Shubham Agrawal, Nikhil Chavan-Dafle, Isaac Kasahara , and 3 more authors
2023
Simultaneous multi-object pose, shape, and grasp estimation can allow inference in real-time for robotic manipulation.
RIC: Rotate-Inpaint-Complete for Generalizable Scene Reconstruction
Isaac Kasahara , Shubham Agrawal, Selim Engin, and 3 more authors
2023
Text-to-image models pre-trained on large amounts of image data can be used to perform generalizable 3D scene reconstruction from a single viewpoint.
2022 Look Both Ways: Self-supervising Driver Gaze Estimation and Road Scene Saliency
Isaac Kasahara , Simon Stent, and Hyun Soo Park
In Computer Vision – ECCV 2022 , 2022
Utilizing saliency information from outside the vehicle can improve the attention estimation of the driver in a self-supervised fashion.
