6 papers
TaskTok: Delving into Task Tokens for Task-driven Image Restoration
Hongjae Lee, Sojung Kang, Jaeseong Yu +1
While traditional image restoration focuses on perceptual quality, Task-Driven Image Restoration (TDIR) aims to maximize the performance of downstream high-level vision tasks. Rece…
LogicIR: Logic Gate Networks for Image Restoration
Hongjae Lee, Myungjun Son, Jaeseong Yu +1
Image restoration aims to reconstruct high-quality images from degraded low-quality inputs. As the computational demands of image restoration models continue to rise, there is grow…
Text Embedding Knows How to Quantize Text-Guided Diffusion Models
Hongjae Lee, Myungjun Son, Dongjea Kang +1
Despite the success of diffusion models in image generation tasks such as text-to-image, the enormous computational complexity of diffusion models limits their use in resource-cons…
RefQSR: Reference-based Quantization for Image Super-Resolution Networks
Hongjae Lee, Jun-Sang Yoo, Seung-Won Jung
Single image super-resolution (SISR) aims to reconstruct a high-resolution image from its low-resolution observation. Recent deep learning-based SISR models show high performance a…
Hierarchical Spatiotemporal Transformers for Video Object Segmentation
Jun-Sang Yoo, Hongjae Lee, Seung-Won Jung
This paper presents a novel framework called HST for semi-supervised video object segmentation (VOS). HST extracts image and video features using the latest Swin Transformer and Vi…
GPS-GLASS: Learning Nighttime Semantic Segmentation Using Daytime Video and GPS data
Hongjae Lee, Changwoo Han, Jun-Sang Yoo +1
Semantic segmentation for autonomous driving should be robust against various in-the-wild environments. Nighttime semantic segmentation is especially challenging due to a lack of a…