a) SfM point cloud (top view) (b) Projected 3D points (c) Synthesized Image (d) Original Image Figure 1: SYNTHESIZING IMAGERY FROM A SFM POINT CLOUD: From left to right: (a) Top view of a SfM reconstruction of an indoor scene, (b) 3D points projected into a viewpoint associated with a source image, (c) the image reconstructed using our technique, and (d) the source image. The reconstructed image is very detailed and closely resembles the source image. AbstractMany 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 [46,9], 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 [24,39] 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.

We present a framework to learn privacy-preserving encodings of images that inhibit inference of chosen private attributes, while allowing recovery of other desirable information. Rather than simply inhibiting a given fixed pretrained estimator, our goal is that an estimator be unable to learn to accurately predict the private attributes even with knowledge of the encoding function. We use a natural adversarial optimization-based formulation for thistraining the encoding function against a classifier for the private attribute, with both modeled as deep neural networks. The key contribution of our work is a stable and convergent optimization approach that is successful at learning an encoder with our desired properties-maintaining utility while inhibiting inference of private attributes, not just within the adversarial optimization, but also by classifiers that are trained after the encoder is fixed. We adopt a rigorous experimental protocol for verification wherein classifiers are trained exhaustively till saturation on the fixed encoders. We evaluate our approach on tasks of real-world complexity-learning high-dimensional encodings that inhibit detection of different scene categories-and find that it yields encoders that are resilient at maintaining privacy.

The next wave of micro and nano devices will create a world with trillions of small networked cameras. This will lead to increased concerns about privacy and security. Most privacy preserving algorithms for computer vision are applied after image/video data has been captured. We propose to use privacy preserving optics that filter or block sensitive information directly from the incident lightfield before sensor measurements are made, adding a new layer of privacy. In addition to balancing the privacy and utility of the captured data, we address trade-offs unique to miniature vision sensors, such as achieving high-quality field-of-view and resolution within the constraints of mass and volume. Our privacy preserving optics enable applications such as depth sensing, full-body motion tracking, people counting, blob detection and privacy preserving face recognition. While we demonstrate applications on macroscale devices (smartphones, webcams, etc.) our theory has impact for smaller devices.

The risk of unauthorized remote access of streaming video from networked cameras underlines the need for stronger privacy safeguards. We propose a lens-free coded aperture camera system for human action recognition that is privacy-preserving. While coded aperture systems exist, we believe ours is the first system designed for action recognition without the need for image restoration as an intermediate step. Action recognition is done using a deep network that takes in as input, non-invertible motion features between pairs of frames computed using phase correlation and log-polar transformation. Phase correlation encodes translation while the log polar transformation encodes inplane rotation and scaling. We show that the translation features are independent of the coded aperture design, as long as its spectral response within the bandwidth has no zeros. Stacking motion features computed on frames at multiple different strides in the video can improve accuracy. Preliminary results on simulated data based on a subset of the UCF and NTU datasets are promising. We also describe our prototype lens-free coded aperture camera system, and results for real captured videos are mixed.

We propose advances that address two key challenges in future trajectory prediction: (i) multimodality in both training data and predictions and (ii) constant time inference regardless of number of agents. Existing trajectory predictions are fundamentally limited by lack of diversity in training data, which is difficult to acquire with sufficient coverage of possible modes. Our first contribution is an automatic method to simulate diverse trajectories in the top-view. It uses pre-existing datasets and maps as initialization, mines existing trajectories to represent realistic driving behaviors and uses a multi-agent vehicle dynamics simulator to generate diverse new trajectories that cover various modes and are consistent with scene layout constraints. Our second contribution is a novel method that generates diverse predictions while accounting for scene semantics and multi-agent interactions, with constant-time inference independent of the number of agents. We propose a convLSTM with novel state pooling operations and losses to predict scene-consistent states of multiple agents in a single forward pass, along with a CVAE for diversity. We validate our proposed multi-agent trajectory prediction approach by training and testing on the proposed simulated dataset and existing real datasets of traffic scenes. In both cases, our approach outperforms SOTA methods by a large margin, highlighting the benefits of both our diverse dataset simulation and constant-time diverse trajectory prediction methods.