Schrödinger's Camera: First Steps Towards a Quantum-Based Privacy Preserving Camera

Privacy-preserving vision must overcome the dual challenge of utility and privacy. Too much anonymity renders the images useless, but too little privacy does not protect sensitive data. We propose a novel design for privacy preservation, where the imagery is stored in quantum states. In the future, this will be enabled by quantum imaging cameras, and, currently, storing very low resolution imagery in quantum states is possible. Quantum state imagery has the advantage of being both private and non-private till the point of measurement. This occurs even when images are manipulated, since every quantum action is fully reversible. We propose a control algorithm, based on double deep Q-learning, to learn how to anonymize the image before measurement. After learning, the RL weights are fixed, and new attack neural networks are trained from scratch to break the system's privacy. Although all our results are in simulation, we demonstrate, with these first steps, that it is possible to control both privacy and utility in a quantum-based manner.

Design of an Adaptive Lightweight LiDAR to Decouple Robot-Camera Geometry

A fundamental challenge in robot perception is the coupling of the sensor pose and robot pose. This has led to research in active vision where robot pose is changed to reorient the sensor to areas of interest for perception. Further, egomotion such as jitter, and external effects such as wind and others affect perception requiring additional effort in software such as image stabilization. This effect is particularly pronounced in micro-air vehicles and micro-robots who typically are lighter and subject to larger jitter but do not have the computational capability to perform stabilization in real-time. We present a novel microelectromechanical (MEMS) mirror LiDAR system to change the field of view of the LiDAR independent of the robot motion. Our design has the potential for use on small, low-power systems where the expensive components of the LiDAR can be placed external to the small robot. We show the utility of our approach in simulation and on prototype hardware mounted on a UAV. We believe that this LiDAR and its compact movable scanning design provide mechanisms to decouple robot and sensor geometry allowing us to simplify robot perception. We also demonstrate examples of motion compensation using IMU and external odometry feedback in hardware.

SaccadeCam: Adaptive Visual Attention for Monocular Depth Sensing

Most monocular depth sensing methods use conventionally captured images that are created without considering scene content. In contrast, animal eyes have fast mechanical motions, called saccades, that control how the scene is imaged by the fovea, where resolution is highest. In this paper, we present the SaccadeCam framework for adaptively distributing resolution onto regions of interest in the scene. Our algorithm for adaptive resolution is a self-supervised network and we demonstrate results for end-to-end learning for monocular depth estimation. We also show preliminary results with a real SaccadeCam hardware prototype.

A MEMS-based Foveating LIDAR to enable Real-time Adaptive Depth Sensing

Most active depth sensors sample their visual field using a fixed pattern, decided by accuracy, speed and cost trade-offs, rather than scene content. However, a number of recent works have demonstrated that adapting measurement patterns to scene content can offer significantly better trade-offs. We propose a hardware LIDAR design that allows flexible real-time measurements according to dynamically specified measurement patterns. Our flexible depth sensor design consists of a controllable scanning LIDAR that can foveate, or increase resolution in regions of interest, and that can fully leverage the power of adaptive depth sensing. We describe our optical setup and calibration, which enables fast sparse depth measurements using a scanning MEMS (micro-electro mechanical) mirror. We validate the efficacy of our prototype LIDAR design by testing on over 75 static and dynamic scenes spanning a range of environments. We also show CNN-based depth-map completion of sparse measurements obtained by our sensor. Our experiments show that our sensor can realize adaptive depth sensing systems.

Revealing Scenes by Inverting Structure from Motion Reconstructions

Many 3D vision systems localize cameras within a scene using 3D point clouds. Such point clouds are often obtained using structure from motion (SfM), after which the images are discarded to preserve privacy. In this paper, we show, for the first time, that such point clouds retain enough information to reveal scene appearance and compromise privacy. We present a privacy attack that reconstructs color images of the scene from the point cloud. Our method is based on a cascaded U-Net that takes as input, a 2D multichannel image of the points rendered from a specific viewpoint containing point depth and optionally color and SIFT descriptors and outputs a color image of the scene from that viewpoint. Unlike previous feature inversion methods, we deal with highly sparse and irregular 2D point distributions and inputs where many point attributes are missing, namely keypoint orientation and scale, the descriptor image source and the 3D point visibility. We evaluate our attack algorithm on public datasets and analyze the significance of the point cloud attributes. Finally, we show that novel views can also be generated thereby enabling compelling virtual tours of the underlying scene.

Learning Privacy Preserving Encodings through Adversarial Training

We present a framework to learn privacy-preserving encodings of images (or other high-dimensional data) to inhibit inference of a chosen private attribute. Rather than encoding a fixed dataset or inhibiting a fixed estimator, we aim to to learn an encoding function such that even after this function is fixed, an estimator with knowledge of the encoding is unable to learn to accurately predict the private attribute, when generalizing beyond a training set. We formulate this as adversarial optimization of an encoding function against a classifier for the private attribute, with both modeled as deep neural networks. We describe an optimization approach which successfully yields an encoder that permanently limits inference of the private attribute, while preserving either a generic notion of information, or the estimation of a different, desired, attribute. We experimentally validate the efficacy of our approach on private tasks of real-world complexity, by learning to prevent detection of scene classes from the Places-365 dataset.