On robust estimation of the location parameter

A morphable model for the synthesis of 3D faces

We describe Human Mesh Recovery (HMR), an end-to-end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that compute 2D or 3D joint locations, we produce a richer and more useful mesh representation that is parameterized by shape and 3D joint angles. The main objective is to minimize the reprojection loss of keypoints, which allows our model to be trained using in-the-wild images that only have ground truth 2D annotations. However, the reprojection loss alone is highly underconstrained. In this work we address this problem by introducing an adversary trained to tell whether human body shape and pose parameters are real or not using a large database of 3D human meshes. We show that HMR can be trained with and without using any paired 2D-to-3D supervision. We do not rely on intermediate 2D keypoint detections and infer 3D pose and shape parameters directly from image pixels. Our model runs in real-time given a bounding box containing the person. We demonstrate our approach on various images in-the-wild and out-perform previous optimization-based methods that output 3D meshes and show competitive results on tasks such as 3D joint location estimation and part segmentation.

/pdf/end-to-end-recovery-of-human-shape-and-pose-3d6yjodltc.pdf

End-to-End Recovery of Human Shape and Pose

We describe the first method to automatically estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image. We estimate a full 3D mesh and show that 2D joints alone carry a surprising amount of information about body shape. The problem is challenging because of the complexity of the human body, articulation, occlusion, clothing, lighting, and the inherent ambiguity in inferring 3D from 2D. To solve this, we first use a recently published CNN-based method, DeepCut, to predict (bottom-up) the 2D body joint locations. We then fit (top-down) a recently published statistical body shape model, called SMPL, to the 2D joints. We do so by minimizing an objective function that penalizes the error between the projected 3D model joints and detected 2D joints. Because SMPL captures correlations in human shape across the population, we are able to robustly fit it to very little data. We further leverage the 3D model to prevent solutions that cause interpenetration. We evaluate our method, SMPLify, on the Leeds Sports, HumanEva, and Human3.6M datasets, showing superior pose accuracy with respect to the state of the art.

/pdf/keep-it-smpl-automatic-estimation-of-3d-human-pose-and-shape-24sdisa762.pdf

Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image

Understanding a visual scene goes beyond recognizing individual objects in isolation. Relationships between objects also constitute rich semantic information about the scene. In this work, we explicitly model the objects and their relationships using scene graphs, a visually-grounded graphical structure of an image. We propose a novel end-to-end model that generates such structured scene representation from an input image. Our key insight is that the graph generation problem can be formulated as message passing between the primal node graph and its dual edge graph. Our joint inference model can take advantage of contextual cues to make better predictions on objects and their relationships. The experiments show that our model significantly outperforms previous methods on the Visual Genome dataset as well as support relation inference in NYU Depth V2 dataset.

/pdf/scene-graph-generation-by-iterative-message-passing-11q7ld5q19.pdf

Scene Graph Generation by Iterative Message Passing

In this paper we propose a multilinear model of human pose and body shape which is estimated from a database of registered 3D body scans in different poses. The model is generated by factorizing the measurements into pose and shape dependent components. By combining it with an ICP based registration method, we are able to estimate pose and body shape of dressed subjects from single images. If several images of the subject are available, shape and poses can be optimized simultaneously for all input images. Additionally, while estimating pose and shape, we use the model as a virtual calibration pattern and also recover the parameters of the perspective camera model the images were created with.

Multilinear pose and body shape estimation of dressed subjects from image sets

Scene understanding is one of the essential and challenging topics in computer vision and photogrammetry. Scene graph provides valuable information for such scene understanding. This paper proposes a novel framework for automatic generation of semantic scene graphs which interpret indoor environments. First, a Convolutional Neural Network is used to detect objects of interest in the given image. Then, the precise support relations between objects are inferred by taking two important auxiliary information in the indoor environments: the physical stability and the prior support knowledge between object categories. Finally, a semantic scene graph describing the contextual relations within a cluttered indoor scene is constructed. In contrast to the previous methods for extracting support relations, our approach provides more accurate results. Furthermore, we do not use pixel-wise segmentation to obtain objects, which is computation costly. We also propose different methods to evaluate the generated scene graphs, which lacks in this community. Our experiments are carried out on the NYUv2 dataset. The experimental results demonstrated that our approach outperforms the state-of-the-art methods in inferring support relations. The estimated scene graphs are accurately compared with ground truth.

On support relations and semantic scene graphs

This article tackles the problem of estimating non-rigid human 3D shape and motion from image sequences taken by uncalibrated cameras. Similar to other state-of-the-art solutions we factorize 2D observations in camera parameters, base poses and mixing coefficients. Existing methods require sufficient camera motion during the sequence to achieve a correct 3D reconstruction. To obtain convincing 3D reconstructions from arbitrary camera motion, our method is based on a-priorly trained base poses. We show that strong periodic assumptions on the coefficients can be used to define an efficient and accurate algorithm for estimating periodic motion such as walking patterns. For the extension to non-periodic motion we propose a novel regularization term based on temporal bone length constancy. In contrast to other works, the proposed method does not use a predefined skeleton or anthropometric constraints and can handle arbitrary camera motion. We achieve convincing 3D reconstructions, even under the influence of noise and occlusions. Multiple experiments based on a 3D error metric demonstrate the stability of the proposed method. Compared to other state-of-the-art methods our algorithm shows a significant improvement.

3D Reconstruction of Human Motion from Monocular Image Sequences

The extension of conventional clustering to hypergraph clustering, which involves higher order similarities instead of pairwise similarities, is increasingly gaining attention in computer vision This is due to the fact that many grouping problems require an affinity measure that must involve a subset of data of size more than two, ie, a hyperedge Almost all previous works, however, have considered the smallest possible hyperedge size, due to a lack of study into the potential benefits of large hyperedges and effective algorithms to generate them In this paper, we show that large hyperedges are better from both theoretical and empirical standpoints We then propose a novel guided sampling strategy for large hyperedges, based on the concept of random cluster models Our method can generate pure large hyperedges that significantly improve grouping accuracy without exponential increases in sampling costs In the important applications of face clustering and motion segmentation, our method demonstrates substantially better accuracy and efficiency

/pdf/clustering-with-hypergraphs-the-case-for-large-hyperedges-588mnthqik.pdf

Clustering with Hypergraphs: The Case for Large Hyperedges

We present a novel approach for vanishing point detection from uncalibrated monocular images. In contrast to state-of-the-art, we make no a priori assumptions about the observed scene. Our method is based on a convolutional neural network (CNN) which does not use natural images, but a Gaussian sphere representation arising from an inverse gnomonic projection of lines detected in an image. This allows us to rely on synthetic data for training, eliminating the need for labelled images. Our method achieves competitive performance on three horizon estimation benchmark datasets. We further highlight some additional use cases for which our vanishing point detection algorithm can be used.

Hanno Ackermann

Papers

Multilinear pose and body shape estimation of dressed subjects from image sets

On support relations and semantic scene graphs

3D Reconstruction of Human Motion from Monocular Image Sequences

Clustering with Hypergraphs: The Case for Large Hyperedges

Deep Learning for Vanishing Point Detection Using an Inverse Gnomonic Projection