5 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…
MASS: Motion-Aligned Selective Scan for Refinement in Flow-Based Video Frame Interpolation
Jun-Sang Yoo, Seung-Won Jung
Video frame interpolation (VFI) remains a challenging task, particularly when dealing with large, non-linear motions and complex occlusions. While flow-based methods are prevalent,…
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…