1 code implementation • 17 Apr 2024 • Yeonguk Yu, Sungho Shin, Seunghyeok Back, Minhwan Ko, Sangjun Noh, Kyoobin Lee
After blocks are adjusted for current test domain, we generate pseudo-labels by averaging given test images and corresponding flipped counterparts.
no code implementations • 5 Dec 2023 • Geonhyup Lee, Joosoon Lee, Sangjun Noh, Minhwan Ko, KangMin Kim, Kyoobin Lee
To enhance extrinsic pose estimation, a multi-point contact strategy is integrated into the model input, recognizing that identical F/T readings can indicate different poses.