Mechanical and Surface Characteristics of Selective Laser Melting-Manufactured Dental Prostheses in Different Processing Stages.

Due to the expansion of the use of powder bed fusion metal additive technologies in the medical field, especially for the realization of dental prostheses, in this paper, the authors propose a comparative experimental study of the mechanical characteristics and the state of their microscale surfaces. The comparison was made from material considerations starting from two dental alloys commonly used to realize dental prostheses: Ni-Cr and Co-Cr, but also technologies for obtaining selective laser melting (SLM) and conventional casting. In addition, to compare the performances with the classical casting technology, for the dental prostheses obtained through SLM, the post-processing stage in which they are in a preliminary finishing and polished state was considered. Therefore, for the determination of important mechanical characteristics and the comparative study of dental prostheses, the indentation test was used, after which the hardness, penetration depths (maximum, permanent, and contact depth), contact stiffness, and contact surface were established, and for the determination of the microtopography of the surfaces, atomic force microscopy (AFM) was used, obtaining the local areal roughness parameters at the miniaturized scale-surface average roughness, root-mean-square roughness (RMS), and peak-to-peak values. Following the research carried out, several interesting conclusions were drawn, and the superiority of the SLM technology over the classic casting method for the production of dental prostheses in terms of some mechanical properties was highlighted. At the same time, the degree of finishing of dental prostheses made by SLM has a significant impact on the mechanical characteristics and especially the local roughness parameters on a miniaturized scale, and if we consider the same degree of finishing, no major differences are observed in the roughness parameters of the surfaces of the prostheses produced by different technologies.

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation.

In this article we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich latent vectors. Instead of simply treating the latent features of nearby frames as positive pairs and those of temporally-distant ones as negative pairs as in other CSS approaches, we explicitly disentangle each latent vector into a time-variant component and a time-invariant one. We then show that applying contrastive loss only to the time-variant features and encouraging a gradual transition on them between nearby and away frames while also reconstructing the input, extract rich temporal features, well-suited for human pose estimation. Our approach reduces error by about 50% compared to the standard CSS strategies, outperforms other unsupervised single-view methods and matches the performance of multi-view techniques. When 2D pose is available, our approach can extract even richer latent features and improve the 3D pose estimation accuracy, outperforming other state-of-the-art weakly supervised methods.

GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss.

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the body and garment shapes. Our network learns to mimic a physics-based simulation (PBS) method while requiring two orders of magnitude less computation time. To train the network, we introduce loss terms inspired by PBS to produce plausible results and make the model collision-aware. To increase the details of the draped garment, we introduce two loss functions that penalize the difference between the curvature of the predicted cloth and PBS. Particularly, we study the impact of mean curvature normal and a novel detail-preserving loss both qualitatively and quantitatively. Our new curvature loss computes the local covariance matrices of the 3D points, and compares the Rayleigh quotients of the prediction and PBS. This leads to more details while performing favorably or comparably against the loss that considers mean curvature normal vectors in the 3D triangulated meshes. We validate our framework on four garment types for various body shapes and poses. Finally, we achieve superior performance against a recently proposed data-driven method.

Self-Supervised Human Detection and Segmentation via Background Inpainting.

While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this when annotating data is prohibitively expensive, we introduce a self-supervised detection and segmentation approach that can work with single images captured by a potentially moving camera. At the heart of our approach lies the observation that object segmentation and background reconstruction are linked tasks, and that, for structured scenes, background regions can be re-synthesized from their surroundings, whereas regions depicting the moving object cannot. We encode this intuition into a self-supervised loss function that we exploit to train a proposal-based segmentation network. To account for the discrete nature of the proposals, we develop a Monte Carlo-based training strategy that allows the algorithm to explore the large space of object proposals. We apply our method to human detection and segmentation in images that visually depart from those of standard benchmarks and outperform existing self-supervised methods.