Výsledky vyhledávání

Report

MeTTA: Single-View to 3D Textured Mesh Reconstruction with Test-Time Adaptation

Autor: Yu-Ji, Kim, Ha, Hyunwoo, Youwang, Kim, Surh, Jaeheung, Ha, Hyowon, Oh, Tae-Hyun

Reconstructing 3D from a single view image is a long-standing challenge. One of the popular approaches to tackle this problem is learning-based methods, but dealing with the test cases unfamiliar with training data (Out-of-distribution; OoD) introduc

Externí odkaz: http://arxiv.org/abs/2408.11465

Zobrazit plný text záznamu

Report

Revisiting Learning-based Video Motion Magnification for Real-time Processing

Autor: Ha, Hyunwoo, Hyun-Bin, Oh, Jun-Seong, Kim, Byung-Ki, Kwon, Sung-Bin, Kim, Tran, Linh-Tam, Kim, Ji-Yun, Bae, Sung-Ho, Oh, Tae-Hyun

Video motion magnification is a technique to capture and amplify subtle motion in a video that is invisible to the naked eye. The deep learning-based prior work successfully demonstrates the modelling of the motion magnification problem with outstand

Externí odkaz: http://arxiv.org/abs/2403.01898

Zobrazit plný text záznamu

Report

Learning-based Axial Video Motion Magnification

Autor: Byung-Ki, Kwon, Hyun-Bin, Oh, Jun-Seong, Kim, Ha, Hyunwoo, Oh, Tae-Hyun

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 scene of interest. This is based on the premise that magnifying small moti

Externí odkaz: http://arxiv.org/abs/2312.09551

Zobrazit plný text záznamu

Report

Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment

Autor: Sung-Bin, Kim, Senocak, Arda, Ha, Hyunwoo, Owens, Andrew, Oh, Tae-Hyun

How does audio describe the world around us? In this paper, we propose a method for generating an image of a scene from sound. Our method addresses the challenges of dealing with the large gaps that often exist between sight and sound. We design a mo

Externí odkaz: http://arxiv.org/abs/2303.17490

Zobrazit plný text záznamu