no code implementations • 3 Jun 2024 • Daekyu Kwon, Dongyoung Kim, Sehwan Ki, Younghyun Jo, Hyong-Euk Lee, Seon Joo Kim
In this work, we propose a novel pretraining framework that constructs a generalizable representation for IQA by selectively extracting quality-related knowledge from VLM and leveraging the scalability of large datasets.
no code implementations • 20 Aug 2023 • Hyunbo Shim, In Cho, Daekyu Kwon, Seon Joo Kim
This paper presents a novel optimization-based method for non-line-of-sight (NLOS) imaging that aims to reconstruct hidden scenes under various setups.