The field of computer vision and 3D reconstruction is rapidly advancing, with significant developments in healthcare and wildlife monitoring. Recent research has focused on creating automated systems for identifying and tracking objects, such as cows, animals, and humans, from videos and images. These systems have the potential to improve livestock management, wildlife conservation, and healthcare outcomes. Notably, deep learning-based techniques are being used to reconstruct 3D models of objects and scenes from RGB images and videos, enabling non-intrusive and accurate assessments. Additionally, computer vision is being applied to medical imaging, such as CT scans, to detect and predict diseases, including COVID-19 and sarcopenia. The use of machine learning models and large-scale datasets is also enabling the development of practical frameworks for 3D wound assessment and BMI estimation from smartphone camera images. Some noteworthy papers include: NeuralMeshing, which presents an automated system for generating geometric models of objects from videos, and HOSt3R, which proposes a keypoint-free approach to estimating hand-object 3D transformations from monocular motion video/images. Wound3DAssist is also a notable framework for 3D wound assessment using monocular consumer-grade videos. Overall, these advances have the potential to transform various fields, including healthcare, wildlife monitoring, and livestock management, by providing accurate, efficient, and non-intrusive assessments and predictions.