We propose a novel computer vision system for reconstructing 3D body shapes from 2D images with the goal of producing highly accurate anthropomorphic measurements from a pair of images. We adopt a supervised learning approach that maps silhouette images to 3D body shapes via a convolutional neural network (CNN). We propose three key improvements over previous approaches: (1) Large-scale realistic synthetic data generation, including more realistic variations in segmentation noise and camera viewpoints. (2) A multi-task learning (MTL) approach to predicting multiple outputs such as shape, 3D joint locations, pose angles, and body volume. (3) A new network architecture that additionally takes known body measurements (e.g., height) and per-pixel segmentation confidence as input. Ablation studies show the improvement in accuracy due to the various components of our system. Results demonstrate that our system produces state-of-the-art results on body circumference errors. We also analyze the repeatability of our system in the presence of realistic camera, background, and pose variations. Our system achieves a vertex standard deviation of ~3mm on the [36] CAESAR dataset.

This paper presents techniques for tracking non-line-of-sight (NLOS) objects using speckle imaging. We develop a novel speckle formation and motion model where both the sensor and the source view objects only indirectly via a diffuse wall. We show that this NLOS imaging scenario is analogous to direct LOS imaging with the wall acting as a virtual, bare (lens-less) sensor. This enables tracking of a single, rigidly moving NLOS object using existing speckle-based motion estimation techniques. However, when imaging multiple NLOS objects, the speckle components due to different objects are superimposed on the virtual bare sensor image, and cannot be analyzed separately for recovering the motion of individual objects. We develop a novel clustering algorithm based on the statistical and geometrical properties of speckle images, which enables identifying the motion trajectories of multiple, independently moving NLOS objects. We demonstrate, for the first time, tracking individual trajectories of multiple objects around a corner with extreme precision (<; 10 microns) using only off-the-shelf imaging components.

We present CoLux, a novel system for measuring micro 3D motion of multiple independently moving objects at macroscopic standoff distances. CoLux is based on speckle imaging, where the scene is illuminated with a coherent light source and imaged with a camera. Coherent light, on interacting with optically rough surfaces, creates a high-frequency speckle pattern in the captured images. The motion of objects results in movement of speckle, which can be measured to estimate the object motion. Speckle imaging is widely used for micro-motion estimation in several applications, including industrial inspection, scientific imaging, and user interfaces (e.g., optical mice). However, current speckle imaging methods are largely limited to measuring 2D motion (parallel to the sensor image plane) of a single rigid object. We develop a novel theoretical model for speckle movement due to multi-object motion, and present a simple technique based on global scale-space speckle motion analysis for measuring small (5--50 microns) compound motion of multiple objects, along all three axes. Using these tools, we develop a method for measuring 3D micro-motion histograms of multiple independently moving objects, without tracking the individual motion trajectories. In order to demonstrate the capabilities of CoLux, we develop a hardware prototype and a proof-of-concept subtle hand gesture recognition system with a broad range of potential applications in user interfaces and interactive computer graphics.

We propose a data-driven approach to facial landmark localization that models the correlations between each landmark and its surrounding appearance features. At runtime, each feature casts a weighted vote to predict landmark locations, where the weight is precomputed to take into account the feature's discriminative power. The feature voting-based landmark detection is more robust than previous local appearance-based detectors, we combine it with nonparametric shape regularization to build a novel facial landmark localization pipeline that is robust to scale, in-plane rotation, occlusion, expression, and most importantly, extreme head pose. We achieve state-of-the-art performance on two especially challenging in-the-wild datasets populated by faces with extreme head pose and expression.

In this work, we propose an exemplar-based face image segmentation algorithm. We take inspiration from previous works on image parsing for general scenes. Our approach assumes a database of exemplar face images, each of which is associated with a hand-labeled segmentation map. Given a test image, our algorithm first selects a subset of exemplar images from the database, Our algorithm then computes a nonrigid warp for each exemplar image to align it with the test image. Finally, we propagate labels from the exemplar images to the test image in a pixel-wise manner, using trained weights to modulate and combine label maps from different exemplars. We evaluate our method on two challenging datasets and compare with two face parsing algorithms and a general scene parsing algorithm. We also compare our segmentation results with contour-based face alignment results, that is, we first run the alignment algorithms to extract contour points and then derive segments from the contours. Our algorithm compares favorably with all previous works on all datasets evaluated.

Current face image retrieval methods achieve impressive results, but lack efficient ways to refine the search, particularly for geometric face attributes. Users cannot easily find faces with slightly more furrowed brows or specific leftward pose shifts, for example. To address this problem, we propose a new face search technique based on shape manipulation that is complementary to current search engines. Users drag one or a small number of contour points, like the bottom of the chin or the corner of an eyebrow, to search for faces similar in shape to the current face, but with updated geometric attributes specific to their edits. For example, the user can drag a mouth corner to find faces with wider smiles, or the tip of the nose to find faces with a specific pose. As part of our system, we propose (1) a novel confidence score for face alignment results that automatically constructs a contour-aligned face database with reasonable alignment accuracy, (2) a simple and straightforward extension of PCA with missing data to tensor analysis, and (3) a new regularized tensor model to compute shape feature vectors for each aligned face, all built upon previous work. To the best of our knowledge, our system demonstrates the first face retrieval approach based chiefly on shape manipulation. We show compelling results on a sizable database of over 10,000 face images captured in uncontrolled environments.

In this paper, we present a new framework for non-rigid structure from motion (NRSFM) that simultaneously addresses three significant challenges: severe occlusion, perspective camera projection, and large non-linear deformation. We introduce a concept called a model graph, which greatly reduces the computational cost of discovering groups of input images that depict consistent 3D shapes. A 3D model is constructed for each input image by traversing the model graph along multiple evolutionary paths. A compressive shape representation is constructed, which (1) consolidates the multiple 3D models for each image reconstructed during model evolution and (2) reduces the number of models needed to represent the input image set. Assuming feature correspondences are known, we demonstrate our algorithm on both real and synthetic data sets that exemplify all three aforementioned challenges.

We propose a novel formulation of stereo matching that considers each pixel as a feature vector. Under this view, matching two or more images can be cast as matching point clouds in feature space. We build a nonparametric depth smoothness model in this space that correlates the image features and depth values. This model induces a sparse graph that links pixels with similar features, thereby converting each point cloud into a connected network. This network defines a neighborhood system that captures pixel grouping hierarchies without resorting to image segmentation. We formulate global stereo matching over this neighborhood system and use graph cuts to match pixels between two or more such networks. We show that our stereo formulation is able to recover surfaces with different orders of smoothness, such as those with high-curvature details and sharp discontinuities. Furthermore, compared to other single-frame stereo methods, our method produces more temporally stable results from videos of dynamic scenes, even when applied to each frame independently.

We describe a method for producing a smooth, stabilized video from the shaky input of a hand-held light field video camera—specifically, a small camera array. Traditional stabilization techniques dampen shake with 2D warps, and thus have limited ability to stabilize a significantly shaky camera motion through a 3D scene. Other recent stabilization techniques synthesize novel views as they would have been seen along a virtual, smooth 3D camera path, but are limited to static scenes. We show that video camera arrays enable much more powerful video stabilization, since they allow changes in viewpoint for a single time instant. Furthermore, we point out that the straightforward approach to light field video stabilization requires computing structure-from-motion, which can be brittle for typical consumer-level video of general dynamic scenes. We present a more robust approach that avoids input camera path reconstruction. Instead, we employ a spacetime optimization that directly computes a sequence of relative poses between the virtual camera and the camera array, while minimizing acceleration of salient visual features in the virtual image plane. We validate our novel method by comparing it to state-of-the-art stabilization software, such as Apple iMovie and 2d3 SteadyMove Pro, on a number of challenging scenes.