← Search

Donggun Kim

4 accepted papers

2026

BEAT2AASIST MODEL WITH LAYER FUSION FOR ESDD 2026 CHALLENGE

ICASSP 2026poster

Recent advances in audio generation have increased the risk of realistic environmental sound manipulation, motivating the ESDD 2026 Challenge as the first large-scale benchmark for Environmental Sound Deepfake Detection (ESDD). We propose BEAT2AASIST which extends BEATs-AASIST by splitting BEATs-der…

Cited by 3SourcePDFScholar
2026

BEAT2AASIST: BEATs Feature Splitting with Dual-Branch AASIST for Environmental Sound Deepfake Detection

IJCAI 2026

Recent advances in text-to-audio (TTA) and audio-to-audio (ATA) generation models have enabled the creation of highly realistic environmental sounds, raising growing concerns about malicious audio manipulation in real-world scenarios. To address this emerging threat, the ESDD 2026 Challenge was intr

Cited by 0Scholar
2025

Splat-based 3D Scene Reconstruction with Extreme Motion-blur

ICCV 2025poster

We propose a splat-based 3D scene reconstruction method from RGB-D input that effectively handles extreme motion blur, a frequent challenge in low-light environments. Under dim illumination, RGB frames often suffer from severe motion blur due to extended exposure times, causing traditional camera po…

Cited by 0SourcePDFScholar
2023

Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image

CVPR 2023poster

Dual-pixel photography is monocular RGB-D photography with an ultra-high resolution, enabling many applications in computational photography. However, there are still several challenges to fully utilizing dual-pixel photography. Unlike the conventional stereo pair, the dual pixel exhibits a bidirect…

Cited by 8SourcePDFScholar