In the field of 3D Human Performance Capture, a high-quality 3D scan of the performer is rigged and skinned to an animatable 3D template mesh that is subsequently fitted to the captured performance's RGB-D data. Template fitting is accomplished via solving for the template's pose parameters that better explain the performance data at each recorded frame. In this paper, we challenge open implementations of zeroth-order optimizers to solve the template fitting problem in a human performance capture dataset. The objective function that we employ approximates, the otherwise costly to evaluate, 3D RMS hausdorff distance between the animated template and the 3D mesh reconstructed from the depth data (target mesh) at an individual recorded frame. We distinguish and benchmark the optimizers, in three different real-world scenarios, two of which are based on the geometric proximity of the template to the target in individual frames, while in the third one we fit the template sequentially to all target frames of the recorded sequence. Conclusions of this work can serve as a reference for future optimizer implementations and our findings can server as a baseline for future multi-objective optimization approaches. We make part of our benchmark and experiment setup publicly available (https://github.com/VCL3D/nevergrad, https://github.com/VCL3D/PerformanceCapture/releases/).

With the advent of consumer grade depth sensors, low-cost volumetric capture systems are easier to deploy. Their wider adoption though depends on their usability and by extension on the practicality of spatially aligning multiple sensors. Most existing alignment approaches employ visual patterns, e.g. checkerboards, or markers and require high user involvement and technical knowledge. More user-friendly and easier-to-use approaches rely on markerless methods that exploit geometric patterns of a physical structure. However, current SoA approaches are bounded by restrictions in the placement and the number of sensors. In this work, we improve markerless data-driven correspondence estimation to achieve more robust and flexible multi-sensor spatial alignment. In particular, we incorporate geometric constraints in an end-to-end manner into a typical segmentation based model and bridge the intermediate dense classification task with the targeted pose estimation one. This is accomplished by a soft, differentiable procrustes analysis that regularizes the segmentation and achieves higher extrinsic calibration performance in expanded sensor placement configurations, while being unrestricted by the number of sensors of the volumetric capture system. Our model is experimentally shown to achieve similar results with marker-based methods and outperform the mark-erless ones, while also being robust to the pose variations of the calibration structure. Code and pretrained models are available at https://vcl3d.github.io/StructureNet/.

Depth perception is considered an invaluable source of information for various vision tasks. However, depth maps acquired using consumer-level sensors still suffer from non-negligible noise. This fact has recently motivated researchers to exploit traditional filters, as well as the deep learning paradigm, in order to suppress the aforementioned non-uniform noise, while preserving geometric details. Despite the effort, deep depth denoising is still an open challenge mainly due to the lack of clean data that could be used as ground truth. In this paper, we propose a fully convolutional deep autoencoder that learns to denoise depth maps, surpassing the lack of ground truth data. Specifically, the proposed autoencoder exploits multiple views of the same scene from different points of view in order to learn to suppress noise in a self-supervised end-to-end manner using depth and color information during training, yet only depth during inference. To enforce self-supervision, we leverage a differentiable rendering technique to exploit photometric supervision, which is further regularized using geometric and surface priors. As the proposed approach relies on raw data acquisition, a large RGB-D corpus is collected using Intel RealSense sensors. Complementary to a quantitative evaluation, we demonstrate the effectiveness of the proposed self-supervised denoising approach on established 3D reconstruction applications. Code is avalable at https://github.com/VCL3D/DeepDepthDenoising.