The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future.

Three-dimensional augmentation in severely atrophic bone and after cancer resection is a challenging clinical indication that is mostly solved using autologous bone transplantation. The development of the digital technique along with the additive manufacturing and three-dimensional (3D) printing opened new avenues for reconstructive oral and maxillofacial surgery. Therefore, patient-specific titanium mesh is a novel means of stabilizing the augmentation region using particulate bone substitute materials (BSMs) combined with autologous bone as a minimally invasive concept. However, dehiscence is a frequently reported complication in this field. Therefore, the aim of the present case series was to introduce a biomaterial-based regenerative concept in terms of exposed open healing to overcome the dehiscence related to 3D-titanium meshes. Additionally, this case series presents a novel protocol using a combination of xenogeneic BSMs with an autologous blood concentrate system (platelet-rich fibrin [PRF]) and collagen matrices without any autologous transplantation. Seven patients with alveolar ridge atrophy with different etiologies (cancer resection, severe atrophy after tooth loss, aplasia, trauma, implant infections) were treated using the open-healing concept. Therefore, after 3D augmentation using the described biomaterials, the flap margins were approximated, and the gap between the flap margins was bridged using a collagen matrix loaded with liquid PRF that was then covered by either a PTFE-based membrane or sterile latex. No periosteum splitting was performed at any time point. After a healing period of 4-8 months, all patients received dental implants as virtually planned. Bone biopsies were performed during dental insertion for histological evaluation. The augmentation area displayed a vital and well-vascularized newly formed bone that incorporated the BSM granules to build a hybrid bone. Additionally, open healing resulted in newly formed soft tissue without any signs of scar formation or fibrosis. The regenerated soft tissue was used to build a new flap during implant insertion and showed good functional and aesthetic results after implant insertion. The open-healing concept of the regeneration of the soft tissue along with bone tissue to regenerate a harmonic implantation bed is a minimally invasive intervention without periosteum splitting or large flap mobilization. However, further controlled clinical studies are needed to evaluate this concept in a larger patient cohort to outline the potential clinical benefit.