arXiv subjects

William T. Freeman

Publications and source records attributed to William T. Freeman.

At least 127 records · Page 7Linked to original sources

arXiv2018

Unsupervised Training for 3D Morphable Model Regression

We present a method for training a regression network from image pixels to 3D morphable model coordinates using only unlabeled photographs. The training loss is based on features from a facial recognition network, computed on-the-fly by rendering the predicted faces with a differentiable renderer. To make training from features feasible and avoid network fooling effects, we introduce three objectives: a batch distribution loss that encourages the output distribution to match the distribution of the morphable model, a loopback loss that ensures the network can correctly reinterpret its own output, and a multi-view identity loss that compares the features of the predicted 3D face and the input photograph from multiple viewing angles. We train a regression network using these objectives, a set of unlabeled photographs, and the morphable model itself, and demonstrate state-of-the-art results.

cs.CV↗

arXiv2018

Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling

We study 3D shape modeling from a single image and make contributions to it in three aspects. First, we present Pix3D, a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related tasks including reconstruction, retrieval, viewpoint estimation, etc. Building such a large-scale dataset, however, is highly challenging; existing datasets either contain only synthetic data, or lack precise alignment between 2D images and 3D shapes, or only have a small number of images. Second, we calibrate the evaluation criteria for 3D shape reconstruction through behavioral studies, and use them to objectively and systematically benchmark cutting-edge reconstruction algorithms on Pix3D. Third, we design a novel model that simultaneously performs 3D reconstruction and pose estimation; our multi-task learning approach achieves state-of-the-art performance on both tasks.

cs.CV↗

arXiv2018

Smart, Sparse Contours to Represent and Edit Images

We study the problem of reconstructing an image from information stored at contour locations. We show that high-quality reconstructions with high fidelity to the source image can be obtained from sparse input, e.g., comprising less than $6\%$ of image pixels. This is a significant improvement over existing contour-based reconstruction methods that require much denser input to capture subtle texture information and to ensure image quality. Our model, based on generative adversarial networks, synthesizes texture and details in regions where no input information is provided. The semantic knowledge encoded into our model and the sparsity of the input allows to use contours as an intuitive interface for semantically-aware image manipulation: local edits in contour domain translate to long-range and coherent changes in pixel space. We can perform complex structural changes such as changing facial expression by simple edits of contours. Our experiments demonstrate that humans as well as a face recognition system mostly cannot distinguish between our reconstructions and the source images.

cs.CV↗

arXiv2018

Reconstructing Video from Interferometric Measurements of Time-Varying Sources

Very long baseline interferometry (VLBI) makes it possible to recover images of astronomical sources with extremely high angular resolution. Most recently, the Event Horizon Telescope (EHT) has extended VLBI to short millimeter wavelengths with a goal of achieving angular resolution sufficient for imaging the event horizons of nearby supermassive black holes. VLBI provides measurements related to the underlying source image through a sparse set spatial frequencies. An image can then be recovered from these measurements by making assumptions about the underlying image. One of the most important assumptions made by conventional imaging methods is that over the course of a night's observation the image is static. However, for quickly evolving sources, such as the galactic center's supermassive black hole (Sgr A*) targeted by the EHT, this assumption is violated and these conventional imaging approaches fail. In this work we propose a new way to model VLBI measurements that allows us to recover both the appearance and dynamics of an evolving source by reconstructing a video rather than a static image. By modeling VLBI measurements using a Gaussian Markov Model, we are able to propagate information across observations in time to reconstruct a video, while simultaneously learning about the dynamics of the source's emission region. We demonstrate our proposed Expectation-Maximization (EM) algorithm, StarWarps, on realistic synthetic observations of black holes, and show how it substantially improves results compared to conventional imaging algorithms. Additionally, we demonstrate StarWarps on real VLBI data of the M87 Jet from the VLBA.

astro-ph.IM↗

arXiv2017

Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning

The sound of crashing waves, the roar of fast-moving cars -- sound conveys important information about the objects in our surroundings. In this work, we show that ambient sounds can be used as a supervisory signal for learning visual models. To demonstrate this, we train a convolutional neural network to predict a statistical summary of the sound associated with a video frame. We show that, through this process, the network learns a representation that conveys information about objects and scenes. We evaluate this representation on several recognition tasks, finding that its performance is comparable to that of other state-of-the-art unsupervised learning methods. Finally, we show through visualizations that the network learns units that are selective to objects that are often associated with characteristic sounds. This paper extends an earlier conference paper, Owens et al. 2016, with additional experiments and discussion.

cs.CV↗

arXiv2017

Exploiting Occlusion in Non-Line-of-Sight Active Imaging

Active non-line-of-sight imaging systems are of growing interest for diverse applications. The most commonly proposed approaches to date rely on exploiting time-resolved measurements, i.e., measuring the time it takes for short light pulses to transit the scene. This typically requires expensive, specialized, ultrafast lasers and detectors that must be carefully calibrated. We develop an alternative approach that exploits the valuable role that natural occluders in a scene play in enabling accurate and practical image formation in such settings without such hardware complexity. In particular, we demonstrate that the presence of occluders in the hidden scene can obviate the need for collecting time-resolved measurements, and develop an accompanying analysis for such systems and their generalizations. Ultimately, the results suggest the potential to develop increasingly sophisticated future systems that are able to identify and exploit diverse structural features of the environment to reconstruct scenes hidden from view.

eess.IV↗

arXiv2017

Synthesizing Normalized Faces from Facial Identity Features

We present a method for synthesizing a frontal, neutral-expression image of a person's face given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition network. Unlike previous approaches, our encoding feature vector is largely invariant to lighting, pose, and facial expression. Exploiting this invariance, we train our decoder network using only frontal, neutral-expression photographs. Since these photographs are well aligned, we can decompose them into a sparse set of landmark points and aligned texture maps. The decoder then predicts landmarks and textures independently and combines them using a differentiable image warping operation. The resulting images can be used for a number of applications, such as analyzing facial attributes, exposure and white balance adjustment, or creating a 3-D avatar.

cs.CV↗

arXiv2017

Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling

We study the problem of 3D object generation. We propose a novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional networks and generative adversarial nets. The benefits of our model are three-fold: first, the use of an adversarial criterion, instead of traditional heuristic criteria, enables the generator to capture object structure implicitly and to synthesize high-quality 3D objects; second, the generator establishes a mapping from a low-dimensional probabilistic space to the space of 3D objects, so that we can sample objects without a reference image or CAD models, and explore the 3D object manifold; third, the adversarial discriminator provides a powerful 3D shape descriptor which, learned without supervision, has wide applications in 3D object recognition. Experiments demonstrate that our method generates high-quality 3D objects, and our unsupervisedly learned features achieve impressive performance on 3D object recognition, comparable with those of supervised learning methods.

cs.CV↗

arXiv2016

Ambient Sound Provides Supervision for Visual Learning

cs.CV↗

arXiv2016

Computational Imaging for VLBI Image Reconstruction

Very long baseline interferometry (VLBI) is a technique for imaging celestial radio emissions by simultaneously observing a source from telescopes distributed across Earth. The challenges in reconstructing images from fine angular resolution VLBI data are immense. The data is extremely sparse and noisy, thus requiring statistical image models such as those designed in the computer vision community. In this paper we present a novel Bayesian approach for VLBI image reconstruction. While other methods often require careful tuning and parameter selection for different types of data, our method (CHIRP) produces good results under different settings such as low SNR or extended emission. The success of our method is demonstrated on realistic synthetic experiments as well as publicly available real data. We present this problem in a way that is accessible to members of the community, and provide a dataset website (vlbiimaging.csail.mit.edu) that facilitates controlled comparisons across algorithms.

astro-ph.IM↗

arXiv2016

A Comparative Evaluation of Approximate Probabilistic Simulation and Deep Neural Networks as Accounts of Human Physical Scene Understanding

Humans demonstrate remarkable abilities to predict physical events in complex scenes. Two classes of models for physical scene understanding have recently been proposed: "Intuitive Physics Engines", or IPEs, which posit that people make predictions by running approximate probabilistic simulations in causal mental models similar in nature to video-game physics engines, and memory-based models, which make judgments based on analogies to stored experiences of previously encountered scenes and physical outcomes. Versions of the latter have recently been instantiated in convolutional neural network (CNN) architectures. Here we report four experiments that, to our knowledge, are the first rigorous comparisons of simulation-based and CNN-based models, where both approaches are concretely instantiated in algorithms that can run on raw image inputs and produce as outputs physical judgments such as whether a stack of blocks will fall. Both approaches can achieve super-human accuracy levels and can quantitatively predict human judgments to a similar degree, but only the simulation-based models generalize to novel situations in ways that people do, and are qualitatively consistent with systematic perceptual illusions and judgment asymmetries that people show.

cs.AI↗

arXiv2016

Single Image 3D Interpreter Network

Understanding 3D object structure from a single image is an important but difficult task in computer vision, mostly due to the lack of 3D object annotations in real images. Previous work tackles this problem by either solving an optimization task given 2D keypoint positions, or training on synthetic data with ground truth 3D information. In this work, we propose 3D INterpreter Network (3D-INN), an end-to-end framework which sequentially estimates 2D keypoint heatmaps and 3D object structure, trained on both real 2D-annotated images and synthetic 3D data. This is made possible mainly by two technical innovations. First, we propose a Projection Layer, which projects estimated 3D structure to 2D space, so that 3D-INN can be trained to predict 3D structural parameters supervised by 2D annotations on real images. Second, heatmaps of keypoints serve as an intermediate representation connecting real and synthetic data, enabling 3D-INN to benefit from the variation and abundance of synthetic 3D objects, without suffering from the difference between the statistics of real and synthesized images due to imperfect rendering. The network achieves state-of-the-art performance on both 2D keypoint estimation and 3D structure recovery. We also show that the recovered 3D information can be used in other vision applications, such as 3D rendering and image retrieval.

cs.CV↗

arXiv2016

Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors

We propose a novel method for template matching in unconstrained environments. Its essence is the Best-Buddies Similarity (BBS), a useful, robust, and parameter-free similarity measure between two sets of points. BBS is based on counting the number of Best-Buddies Pairs (BBPs)--pairs of points in source and target sets, where each point is the nearest neighbor of the other. BBS has several key features that make it robust against complex geometric deformations and high levels of outliers, such as those arising from background clutter and occlusions. We study these properties, provide a statistical analysis that justifies them, and demonstrate the consistent success of BBS on a challenging real-world dataset while using different types of features.

cs.CV↗

arXiv2016

Observing---and Imaging---Active Galactic Nuclei with the Event Horizon Telescope

Originally developed to image the shadow region of the central black hole in Sagittarius A* and in the nearby galaxy M87, the Event Horizon Telescope (EHT) provides deep, very high angular resolution data on other AGN sources too. The challenges of working with EHT data have spurred the development of new image reconstruction algorithms. This work briefly reviews the status of the EHT and its utility for observing AGN sources, with emphasis on novel imaging techniques that offer the promise of better reconstructions at 1.3 mm and other wavelengths.

astro-ph.IM↗

arXiv2016

Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks

We study the problem of synthesizing a number of likely future frames from a single input image. In contrast to traditional methods, which have tackled this problem in a deterministic or non-parametric way, we propose a novel approach that models future frames in a probabilistic manner. Our probabilistic model makes it possible for us to sample and synthesize many possible future frames from a single input image. Future frame synthesis is challenging, as it involves low- and high-level image and motion understanding. We propose a novel network structure, namely a Cross Convolutional Network to aid in synthesizing future frames; this network structure encodes image and motion information as feature maps and convolutional kernels, respectively. In experiments, our model performs well on synthetic data, such as 2D shapes and animated game sprites, as well as on real-wold videos. We also show that our model can be applied to tasks such as visual analogy-making, and present an analysis of the learned network representations.

cs.CV↗

arXiv2016

Visually Indicated Sounds

Objects make distinctive sounds when they are hit or scratched. These sounds reveal aspects of an object's material properties, as well as the actions that produced them. In this paper, we propose the task of predicting what sound an object makes when struck as a way of studying physical interactions within a visual scene. We present an algorithm that synthesizes sound from silent videos of people hitting and scratching objects with a drumstick. This algorithm uses a recurrent neural network to predict sound features from videos and then produces a waveform from these features with an example-based synthesis procedure. We show that the sounds predicted by our model are realistic enough to fool participants in a "real or fake" psychophysical experiment, and that they convey significant information about material properties and physical interactions.

cs.CV↗

arXiv2014

Imaging an Event Horizon: Mitigation of Scattering Toward Sagittarius A*

The image of the emission surrounding the black hole in the center of the Milky Way is predicted to exhibit the imprint of general relativistic (GR) effects, including the existence of a shadow feature and a photon ring of diameter ~50 microarcseconds. Structure on these scales can be resolved by millimeter-wavelength very long baseline interferometry (VLBI). However, strong-field GR features of interest will be blurred at lambda >= 1.3 mm due to scattering by interstellar electrons. The scattering properties are well understood over most of the relevant range of baseline lengths, suggesting that the scattering may be (mostly) invertible. We simulate observations of a model image of Sgr A* and demonstrate that the effects of scattering can indeed be mitigated by correcting the visibilities before reconstructing the image. This technique is also applicable to Sgr A* at longer wavelengths.

astro-ph.IM↗

arXiv2012

Exploiting compositionality to explore a large space of model structures

The recent proliferation of richly structured probabilistic models raises the question of how to automatically determine an appropriate model for a dataset. We investigate this question for a space of matrix decomposition models which can express a variety of widely used models from unsupervised learning. To enable model selection, we organize these models into a context-free grammar which generates a wide variety of structures through the compositional application of a few simple rules. We use our grammar to generically and efficiently infer latent components and estimate predictive likelihood for nearly 2500 structures using a small toolbox of reusable algorithms. Using a greedy search over our grammar, we automatically choose the decomposition structure from raw data by evaluating only a small fraction of all models. The proposed method typically finds the correct structure for synthetic data and backs off gracefully to simpler models under heavy noise. It learns sensible structures for datasets as diverse as image patches, motion capture, 20 Questions, and U.S. Senate votes, all using exactly the same code.

cs.LG↗