BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling

1 code implementation • CVPR 2023 • Hyo-Jun Lee, HanUl Kim, Su-Min Choi, Seong-Gyun Jeong, Yeong Jun Koh

A novel monocular 3D pose and shape reconstruction algorithm, based on bi-contextual attention and attention-guided modeling (BAAM), is proposed in this work.

3D Car Instance Understanding Object

Local Connectivity-Based Density Estimation for Face Clustering

1 code implementation • CVPR 2023 • Junho Shin, Hyo-Jun Lee, Hyunseop Kim, Jong-Hyeon Baek, Daehyun Kim, Yeong Jun Koh

For this purpose, we propose a reliable density estimation algorithm based on local connectivity between K nearest neighbors (KNN).

Clustering Connectivity Estimation +2

Luminance-aware Color Transform for Multiple Exposure Correction

1 code implementation • ICCV 2023 • Jong-Hyeon Baek, Daehyun Kim, Su-Min Choi, Hyo-Jun Lee, HanUl Kim, Yeong Jun Koh

Images captured with irregular exposures inevitably present unsatisfactory visual effects, such as distorted hue and color tone.