More Like this

1. A Pose Proposal and Refinement Network for Better 6D Object Pose Estimation

   https://doi.org/10.1109/WACV48630.2021.00243  

   Trabelsi, Ameni ; Chaabane, Mohamed ; Blanchard, Nathaniel ; Beveridge, Ross ( January 2021 , IEEE Winter Conference on Applications of Computer Vision)
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. RFID-Pose: Vision-Aided Three-Dimensional Human Pose Estimation With Radio-Frequency Identification

   https://doi.org/10.1109/TR.2020.3030952  

   Yang, Chao ; Wang, Xuyu ; Mao, Shiwen ( September 2021 , IEEE Transactions on Reliability)
4. A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

   Zhao, Qitao ; Zhang, Ce ; Liu, Mengyuan ; Chen, Chen ( September 2023 , Thirty-Seventh Annual Conference on Neural Information Processing Systems (NeurIPS))
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