1 code implementation • 7 Mar 2024 • Chaehyeon Song, Jaeho Shin, Myung-Hwan Jeon, Jongwoo Lim, Ayoung Kim
Although conics are more informative features than points, the loss of the conic property under distortion has critically limited the utility of conic features in camera calibration.
no code implementations • 11 Jul 2023 • Jeongyun Kim, Myung-Hwan Jeon, Sangwoo Jung, Wooseong Yang, Minwoo Jung, Jaeho Shin, Ayoung Kim
Transparent objects are encountered frequently in our daily lives, yet recognizing them poses challenges for conventional vision sensors due to their unique material properties, not being well perceived from RGB or depth cameras.
1 code implementation • 30 Jan 2023 • Dong-Guw Lee, Myung-Hwan Jeon, Younggun Cho, Ayoung Kim
The insufficient number of annotated thermal infrared (TIR) image datasets not only hinders TIR image-based deep learning networks to have comparable performances to that of RGB but it also limits the supervised learning of TIR image-based tasks with challenging labels.
no code implementations • 2 Nov 2022 • Myung-Hwan Jeon, Jeongyun Kim, Jee-Hwan Ryu, Ayoung Kim
Tackling these limitations, we present an ambiguity-aware 6D object pose estimation network, PrimA6D++, as a generic uncertainty prediction method.