Search Results - "Bae, Soonmin"

Defocus Magnification by Bae, Soonmin, Durand, Frédo

“…A blurry background due to shallow depth of field is often desired for photographs such as portraits, but, unfortunately, small point‐and‐shoot cameras do not…”
Get full text

Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning by Hwang, Dong-Hyun, Kim, Suntae, Monet, Nicolas, Koike, Hideki, Bae, Soonmin

“…We present MoVNect, a lightweight deep neural network to capture 3D human pose using a single RGB camera. To improve the overall performance of the model, we…”
Get full text

Building a Videorama with Shallow Depth of Field by Soonmin Bae, Hao Jiang

“…This paper presents a new automatic approach to building a videorama with shallow depth of field. We stitch the static background of video frames and render…”
Get full text

Image-based querying of urban photos and videos by Cho, Peter, Soonmin Bae, Durand, Fredo

“…We extend recent automated computer vision algorithms to reconstruct the global three-dimensional structures for photos and videos shot at fixed points in…”
Get full text

Regularization on Spatio-Temporally Smoothed Feature for Action Recognition by Kim, Jinhyung, Cha, Seunghwan, Wee, Dongyoon, Bae, Soonmin, Kim, Junmo

“…Deep neural networks for video action recognition frequently require 3D convolutional filters and often encounter overfitting due to a larger number of…”
Get full text

Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning by Hwang, Dong-Hyun, Kim, Suntae, Monet, Nicolas, Koike, Hideki, Bae, Soonmin

“…We present MoVNect, a lightweight deep neural network to capture 3D human pose using a single RGB camera. To improve the overall performance of the model, we…”
Get full text