This work addresses the problem of estimating the full body 3D human pose and shape from a single color image. This is a task where iterative optimization-based solutions have typically prevailed, while Convolutional Networks (ConvNets) have suffered because of the lack of training data and their low resolution 3D predictions. Our work aims to bridge this gap and proposes an efficient and effective direct prediction method based on ConvNets. Central part to our approach is the incorporation of a parametric statistical body shape model (SMPL) within our end-to-end framework. This allows us to get very detailed 3D mesh results, while requiring estimation only of a small number of parameters, making it friendly for direct network prediction. Interestingly, we demonstrate that these parameters can be predicted reliably only from 2D keypoints and masks. These are typical outputs of generic 2D human analysis ConvNets, allowing us to relax the massive requirement that images with 3D shape ground truth are available for training. Simultaneously, by maintaining differentiability, at training time we generate the 3D mesh from the estimated parameters and optimize explicitly for the surface using a 3D per-vertex loss. Finally, a differentiable renderer is employed to project the 3D mesh to the image, which enables further refinement of the network, by optimizing for the consistency of the projection with 2D annotations (i.e., 2D keypoints or masks). The proposed approach outperforms previous baselines on this task and offers an attractive solution for direct prediction of3D shape from a single color image.

/pdf/learning-to-estimate-3d-human-pose-and-shape-from-a-single-lnr1vkco9z.pdf

Learning to Estimate 3D Human Pose and Shape from a Single Color Image

This paper describes a method for scene reconstruction of complex, detailed environments from 3D light fields. Densely sampled light fields in the order of 109 light rays allow us to capture the real world in unparalleled detail, but efficiently processing this amount of data to generate an equally detailed reconstruction represents a significant challenge to existing algorithms. We propose an algorithm that leverages coherence in massive light fields by breaking with a number of established practices in image-based reconstruction. Our algorithm first computes reliable depth estimates specifically around object boundaries instead of interior regions, by operating on individual light rays instead of image patches. More homogeneous interior regions are then processed in a fine-to-coarse procedure rather than the standard coarse-to-fine approaches. At no point in our method is any form of global optimization performed. This allows our algorithm to retain precise object contours while still ensuring smooth reconstructions in less detailed areas. While the core reconstruction method handles general unstructured input, we also introduce a sparse representation and a propagation scheme for reliable depth estimates which make our algorithm particularly effective for 3D input, enabling fast and memory efficient processing of "Gigaray light fields" on a standard GPU. We show dense 3D reconstructions of highly detailed scenes, enabling applications such as automatic segmentation and image-based rendering, and provide an extensive evaluation and comparison to existing image-based reconstruction techniques.

Scene reconstruction from high spatio-angular resolution light fields

Designing and simulating realistic clothing is challenging. Previous methods addressing the capture of clothing from 3D scans have been limited to single garments and simple motions, lack detail, or require specialized texture patterns. Here we address the problem of capturing regular clothing on fully dressed people in motion. People typically wear multiple pieces of clothing at a time. To estimate the shape of such clothing, track it over time, and render it believably, each garment must be segmented from the others and the body. Our ClothCap approach uses a new multi-part 3D model of clothed bodies, automatically segments each piece of clothing, estimates the minimally clothed body shape and pose under the clothing, and tracks the 3D deformations of the clothing over time. We estimate the garments and their motion from 4D scans; that is, high-resolution 3D scans of the subject in motion at 60 fps. ClothCap is able to capture a clothed person in motion, extract their clothing, and retarget the clothing to new body shapes; this provides a step towards virtual try-on.

/pdf/clothcap-seamless-4d-clothing-capture-and-retargeting-405kxfnban.pdf

ClothCap: seamless 4D clothing capture and retargeting

Light field imaging has emerged as a technology allowing to capture richer visual information from our world. As opposed to traditional photography, which captures a 2D projection of the light in the scene integrating the angular domain, light fields collect radiance from rays in all directions, demultiplexing the angular information lost in conventional photography. On the one hand, this higher dimensional representation of visual data offers powerful capabilities for scene understanding, and substantially improves the performance of traditional computer vision problems such as depth sensing, post-capture refocusing, segmentation, video stabilization, material classification, etc. On the other hand, the high-dimensionality of light fields also brings up new challenges in terms of data capture, data compression, content editing, and display. Taking these two elements together, research in light field image processing has become increasingly popular in the computer vision, computer graphics, and signal processing communities. In this paper, we present a comprehensive overview and discussion of research in this field over the past 20 years. We focus on all aspects of light field image processing, including basic light field representation and theory, acquisition, super-resolution, depth estimation, compression, editing, processing algorithms for light field display, and computer vision applications of light field data.

/pdf/light-field-image-processing-an-overview-3jq61afb1y.pdf

Light Field Image Processing: An Overview

Human shape estimation is an important task for video editing, animation and fashion industry. Predicting 3D human body shape from natural images, however, is highly challenging due to factors such as variation in human bodies, clothing and viewpoint. Prior methods addressing this problem typically attempt to fit parametric body models with certain priors on pose and shape. In this work we argue for an alternative representation and propose BodyNet, a neural network for direct inference of volumetric body shape from a single image. BodyNet is an end-to-end trainable network that benefits from (i) a volumetric 3D loss, (ii) a multi-view re-projection loss, and (iii) intermediate supervision of 2D pose, 2D body part segmentation, and 3D pose. Each of them results in performance improvement as demonstrated by our experiments. To evaluate the method, we fit the SMPL model to our network output and show state-of-the-art results on the SURREAL and Unite the People datasets, outperforming recent approaches. Besides achieving state-of-the-art performance, our method also enables volumetric body-part segmentation.

/pdf/bodynet-volumetric-inference-of-3d-human-body-shapes-yi2mlgd356.pdf

BodyNet: Volumetric Inference of 3D Human Body Shapes

We represent human body shape estimation from binary silhouettes or shaded images as a regression problem, and describe a novel method to tackle it using CNNs. Utilizing a parametric body model, we train CNNs to learn a global mapping from the input to shape parameters used to reconstruct the shapes of people, in neutral poses, with the application of garment fitting in mind. This results in an accurate, robust and automatic system, orders of magnitude faster than methods we compare to, enabling interactive applications. In addition, we show how to combine silhouettes from two views to improve prediction over a single view. The method is extensively evaluated on thousands of synthetic shapes and real data and compared to state of-art approaches, clearly outperforming methods based on global fitting and strongly competing with more expensive local fitting based ones.

HS-Nets: Estimating Human Body Shape from Silhouettes with Convolutional Neural Networks

In this work, we present a novel method for capturing human body shape from a single scaled silhouette. We combine deep correlated features capturing different 2D views, and embedding spaces based on 3D cues in a novel convolutional neural network (CNN) based architecture. We first train a CNN to find a richer body shape representation space from pose invariant 3D human shape descriptors. Then, we learn a mapping from silhouettes to this representation space, with the help of a novel architecture that exploits correlation of multi-view data during training time, to improve prediction at test time. We extensively validate our results on synthetic and real data, demonstrating significant improvements in accuracy as compared to the state-of-the-art, and providing a practical system for detailed human body measurements from a single image.

/pdf/human-shape-from-silhouettes-using-generative-hks-4a3ucng8tc.pdf

Human Shape from Silhouettes Using Generative HKS Descriptors and Cross-Modal Neural Networks

3D garment capture is an important component for various applications such as free-view point video, virtual avatars, online shopping, and virtual cloth fitting. Due to the complexity of the deformations, capturing 3D garment shapes requires controlled and specialized setups. A viable alternative is image-based garment capture. Capturing 3D garment shapes from a single image, however, is a challenging problem and the current solutions come with assumptions on the lighting, camera calibration, complexity of human or mannequin poses considered, and more importantly a stable physical state for the garment and the underlying human body. In addition, most of the works require manual interaction and exhibit high run-times. We propose a new technique that overcomes these limitations, making garment shape estimation from an image a practical approach for dynamic garment capture. Starting from synthetic garment shape data generated through physically based simulations from various human bodies in complex poses obtained through Mocap sequences, and rendered under varying camera positions and lighting conditions, our novel method learns a mapping from rendered garment images to the underlying 3D garment model. This is achieved by training Convolutional Neural Networks CNN-s to estimate 3D vertex displacements from a template mesh with a specialized loss function. We illustrate that this technique is able to recover the global shape of dynamic 3D garments from a single image under varying factors such as challenging human poses, self occlusions, various camera poses and lighting conditions, at interactive rates. Improvement is shown if more than one view is integrated. Additionally, we show applications of our method to videos.

DeepGarment: 3D Garment Shape Estimation from a Single Image

A computer-implemented method for estimating a pose of an articulated object model (4), wherein the articulated object model (4) is a computer based 3D model (1) of a real world object (14) observed by one or more source cameras (9), and wherein the pose of the articulated object model (4) is defmed by the spatial location of joints (2) of the articulated object model (4), comprises the steps of 
• obtaining a source image (10) from a video stream ; 
• processing the source image (10) to extract a source image segment (13); 
• maintaining, in a database, a set of reference silhouettes , each being associated with an articulated object model (4) and a corresponding reference pose ; 
• comparing the source image segment (13) to the reference silhouettes and selecting reference silhouettes by taking into account, for each reference silhouette, 
o a matching error that indicates how closely the reference silhouette matches the source image segment (13) and/or 
o a coherence error that indicates how much the reference pose is consistent with the pose of the same real world object (14) as estimated from a preceding source image (10); 
• retrieving the corresponding reference poses of the articulated object models (4); and 
• computing an estimate of the pose of the articulated object model (4) from the reference poses of the selected reference silhouettes.

Method for estimating a pose of an articulated object model

We present a novel representation and rendering method for free-viewpoint video of human characters based on multiple input video streams. The basic idea is to approximate the articulated 3D shape of the human body using a subdivision into textured billboards along the skeleton structure. Billboards are clustered to fans such that each skeleton bone contains one billboard per source camera. We call this representation articulated billboards.



In the paper we describe a semi-automatic, data-driven algorithm to construct and render this representation, which robustly handles even challenging acquisition scenarios characterized by sparse camera positioning, inaccurate camera calibration, low video resolution, or occlusions in the scene. First, for each input view, a 2D pose estimation based on image silhouettes, motion capture data, and temporal video coherence is used to create a segmentation mask for each body part. Then, from the 2D poses and the segmentation, the actual articulated billboard model is constructed by a 3D joint optimization and compensation for camera calibration errors. The rendering method includes a novel way of blending the textural contributions of each billboard and features an adaptive seam correction to eliminate visible discontinuities between adjacent billboards textures.



Our articulated billboards do not only minimize ghosting artifacts known from conventional billboard rendering, but also alleviate restrictions to the setup and sensitivities to errors of more complex 3D representations and multiview reconstruction techniques. Our results demonstrate the flexibility and the robustness of our approach with high quality free-viewpoint video generated from broadcast footage of challenging, uncontrolled environments.

Remo Ziegler

Papers

HS-Nets: Estimating Human Body Shape from Silhouettes with Convolutional Neural Networks

Human Shape from Silhouettes Using Generative HKS Descriptors and Cross-Modal Neural Networks

DeepGarment: 3D Garment Shape Estimation from a Single Image

Method for estimating a pose of an articulated object model

Articulated Billboards for Video‐based Rendering