The field of 3D human reconstruction and animation is rapidly advancing, with a focus on developing more accurate and efficient methods for estimating human pose, reconstructing 3D models, and animating digital avatars. Recent research has explored the use of deep learning techniques, such as transformers and convolutional neural networks, to improve the accuracy and robustness of these methods. Additionally, there is a growing interest in developing methods that can handle complex scenarios, such as human-centric environments and uncalibrated cameras. Notable papers in this area include: SAT, which proposes a two-process framework for monocular texture 3D human reconstruction, achieving state-of-the-art results on several benchmarks. PersPose, which introduces a novel 3D human pose estimation framework that incorporates perspective encoding and rotation, achieving state-of-the-art performance on several datasets. PriorFormer, which proposes a lightweight transformer-based lifter for real-time monocular 3D human pose estimation, outperforming existing methods in terms of accuracy and computational efficiency. COMETH, which presents a lightweight algorithm for real-time multi-view human pose fusion, enabling accurate and scalable human motion tracking for industrial and safety-critical applications.