6 papers
Linear Recurrent Unit with Semantic Modulation for Image Super-Resolution
Mingyu Choi, Woo Kyoung Han, Sunghoon Im +1
Linear recurrent unit (LRU), designed with a principled formulation for stable linear recurrence, has demonstrated promising accuracy and robustness on long-range dependency tasks.…
Balancing Fidelity and Diversity in Diffusion Models via Symmetric Attention Decomposition: Hopfield Perspective
Hyunmin Cho, Woo Kyoung Han, Kyong Hwan Jin
We characterize the pre-softmax attention matrix in transformers as an associative memory matrix encoding pairwise associations between input features. By decomp…
JPEG Processing Neural Operator for Backward-Compatible Coding
Woo Kyoung Han, Yongjun Lee, Byeonghun Lee +3
Despite significant advances in learning-based lossy compression algorithms, standardizing codecs remains a critical challenge. In this paper, we present the JPEG Processing Neural…
Towards Lossless Implicit Neural Representation via Bit Plane Decomposition
Woo Kyoung Han, Byeonghun Lee, Hyunmin Cho +2
We quantify the upper bound on the size of the implicit neural representation (INR) model from a digital perspective. The upper bound of the model size increases exponentially as t…
JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients
Woo Kyoung Han, Sunghoon Im, Jaedeok Kim +1
We propose a practical approach to JPEG image decoding, utilizing a local implicit neural representation with continuous cosine formulation. The JPEG algorithm significantly quanti…
Learning Residual Elastic Warps for Image Stitching under Dirichlet Boundary Condition
Minsu Kim, Yongjun Lee, Woo Kyoung Han +1
Trendy suggestions for learning-based elastic warps enable the deep image stitchings to align images exposed to large parallax errors. Despite the remarkable alignments, the method…