More Like this

1. Pose Relation Transformer Refine Occlusions for Human Pose Estimation

   https://doi.org/10.1109/ICRA48891.2023.10161259  

   Chi, Hyung-gun; Chi, Seunggeun; Chan, Stanley; Ramani, Karthik (May 2023, IEEE)
2. Pose Flow Learning From Person Images for Pose Guided Synthesis

   https://doi.org/10.1109/TIP.2020.3031108  

   Zheng, Haitian; Chen, Lele; Xu, Chenliang; Luo, Jiebo (January 2021, IEEE Transactions on Image Processing)
3. TAX-Pose: Task-Specific Cross-Pose Estimation for Robot Manipulation

   Chuer Pan, Brian Okorn (November 2022, arXivorg)
4. Ring-a-Pose: A Ring for Continuous Hand Pose Tracking

   https://doi.org/10.1145/3699741  

   Yu, Tianhong Catherine; Hu, Guilin; Zhang, Ruidong; Lim, Hyunchul; Mahmud, Saif; Lee, Chi-Jung; Li, Ke; Agarwal, Devansh; Nie, Shuyang; Oh, Jinseok; et al (November 2024, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies)

   We present Ring-a-Pose, a single untethered ring that tracks continuous 3D hand poses. Located in the center of the hand, the ring emits an inaudible acoustic signal that each hand pose reflects differently. Ring-a-Pose imposes minimal obtrusions on the hand, unlike multi-ring or glove systems. It is not affected by the choice of clothing that may cover wrist-worn systems. In a series of three user studies with a total of 36 participants, we evaluate Ring-a-Pose's performance on pose tracking and micro-finger gesture recognition. Without collecting any training data from a user, Ring-a-Pose tracks continuous hand poses with a joint error of 14.1mm. The joint error decreases to 10.3mm for fine-tuned user-dependent models. Ring-a-Pose recognizes 7-class micro-gestures with a 90.60% and 99.27% accuracy for user-independent and user-dependent models, respectively. Furthermore, the ring exhibits promising performance when worn on any finger. Ring-a-Pose enables the future of smart rings to track and recognize hand poses using relatively low-power acoustic sensing. 

   more » « less
5. Camera Pose Matters: Improving Depth Prediction by Mitigating Pose Distribution Bias

   Zhao, Y; Kong, S; Fowlkes, C (June 2021, IEEE Computer Society Conference on Computer Vision and Pattern Recognition)

   null (Ed.)

   Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predic- tors fail to make reliable depth predictions for testing exam- ples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we in- troduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consis- tent manner. Second, we propose a conditional model that exploits the per-image camera pose as prior knowledge by encoding it as a part of the input. We show that jointly ap- plying the two methods improves depth prediction on im- ages captured under uncommon and even never-before-seen camera poses. We show that our methods improve perfor- mance when applied to a range of different predictor ar- chitectures. Lastly, we show that explicitly encoding the camera pose distribution improves the generalization per- formance of a synthetically trained depth predictor when evaluated on real images. 

   more » « less