4 papers
DarkQA: Benchmarking Vision-Language Models on Visual-Primitive Question Answering in Low-Light Indoor Scenes
Yohan Park, Hyunwoo Ha, Wonjun Jo +1
Vision Language Models (VLMs) are increasingly adopted as central reasoning modules for embodied agents. Existing benchmarks evaluate their capabilities under ideal, well-lit condi…
LiDAR-Anchored Collaborative Distillation for Robust 2D Representations
Wonjun Jo, Hyunwoo Ha, Kim Ji-Yeon +2
As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for various downstream tasks,…
Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment
Kim Sung-Bin, Arda Senocak, Hyunwoo Ha +1
How does audio describe the world around us? In this work, we propose a method for generating images of visual scenes from diverse in-the-wild sounds. This cross-modal generation t…
Learning-based Axial Video Motion Magnification
Kwon Byung-Ki, Oh Hyun-Bin, Kim Jun-Seong +2
Video motion magnification amplifies invisible small motions to be perceptible, which provides humans with a spatially dense and holistic understanding of small motions in the scen…