Search Results for author: Seung-Hun Nam

Found 9 papers, 2 papers with code

Imperceptible Protection against Style Imitation from Diffusion Models

no code implementations28 Mar 2024 Namhyuk Ahn, Wonhyuk Ahn, KiYoon Yoo, Daesik Kim, Seung-Hun Nam

Recent progress in diffusion models has profoundly enhanced the fidelity of image generation.

Image Generation

A Framework for Portrait Stylization with Skin-Tone Awareness and Nudity Identification

no code implementations21 Mar 2024 Seungkwon Kim, Sangyeon Kim, Seung-Hun Nam

Portrait stylization is a challenging task involving the transformation of an input portrait image into a specific style while preserving its inherent characteristics.

DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models

no code implementations13 Sep 2023 Namhyuk Ahn, Junsoo Lee, Chunggi Lee, Kunhee Kim, Daesik Kim, Seung-Hun Nam, Kibeom Hong

Recent progresses in large-scale text-to-image models have yielded remarkable accomplishments, finding various applications in art domain.

Image Generation Style Transfer

DHNet: Double MPEG-4 Compression Detection via Multiple DCT Histograms

no code implementations19 Jul 2021 Seung-Hun Nam, Wonhyuk Ahn, Myung-Joon Kwon, Jihyeon Kang, In-Jae Yu

In this article, we aim to detect the double compression of MPEG-4, a universal video codec that is built into surveillance systems and shooting devices.

Quantization

Frame-rate Up-conversion Detection Based on Convolutional Neural Network for Learning Spatiotemporal Features

no code implementations25 Mar 2021 Minseok Yoon, Seung-Hun Nam, In-Jae Yu, Wonhyuk Ahn, Myung-Joon Kwon, Heung-Kyu Lee

The proposed network uses a stack of consecutive frames as the input and effectively learns interpolation artifacts using network blocks to learn spatiotemporal features.

Video Editing Video Forensics

WAN: Watermarking Attack Network

no code implementations14 Aug 2020 Seung-Hun Nam, In-Jae Yu, Seung-Min Mun, Daesik Kim, Wonhyuk Ahn

Multi-bit watermarking (MW) has been developed to improve robustness against signal processing operations and geometric distortions.

Deep Convolutional Neural Network for Identifying Seam-Carving Forgery

no code implementations5 Jul 2020 Seung-Hun Nam, Wonhyuk Ahn, In-Jae Yu, Myung-Joon Kwon, Minseok Son, Heung-Kyu Lee

Seam carving is a representative content-aware image retargeting approach to adjust the size of an image while preserving its visually prominent content.

Image Forensics Image Retargeting

BitMix: Data Augmentation for Image Steganalysis

1 code implementation30 Jun 2020 In-Jae Yu, Wonhyuk Ahn, Seung-Hun Nam, Heung-Kyu Lee

Convolutional neural networks (CNN) for image steganalysis demonstrate better performances with employing concepts from high-level vision tasks.

Data Augmentation Steganalysis

Cannot find the paper you are looking for? You can Submit a new open access paper.