Semantic segmentation, which aims to classify every pixel in an image, is a key task in machine perception, with many applications across robotics and autonomous driving. Due to the high dimensionality of this task, most existing approaches use local operations, such as convolutions, to generate per-pixel features. However, these methods are typically unable to effectively leverage global context information due to the high computational costs of operating on a dense image. In this work, we propose a solution to this issue by leveraging the idea of superpixels, an over-segmentation of the image, and applying them with a modern transformer framework. In particular, our model learns to decompose the pixel space into a spatially low dimensional superpixel space via a series of local cross-attentions. We then apply multi-head self-attention to the superpixels to enrich the superpixel features with global context and then directly produce a class prediction for each superpixel. Finally, we directly project the superpixel class predictions back into the pixel space using the associations between the superpixels and the image pixel features. Reasoning in the superpixel space allows our method to be substantially more computationally efficient compared to convolution-based decoder methods. Yet, our method achieves state-of-the-art performance in semantic segmentation due to the rich superpixel features generated by the global self-attention mechanism. Our experiments on Cityscapes and ADE20K demonstrate that our method matches the state of the art in terms of accuracy, while outperforming in terms of model parameters and latency.

Segmenting object instances is a key task in machine perception, with safety-critical applications in robotics and autonomous driving. We introduce a novel approach to instance segmentation that jointly leverages measurements from multiple sensor modalities, such as cameras and LiDAR. Our method learns to predict embeddings for each pixel or point that give rise to a dense segmentation of the scene. Specifically, our technique applies contrastive learning to points in the scene both across sensor modalities and the temporal domain. We demonstrate that this formulation encourages the models to learn embeddings that are invariant to viewpoint variations and consistent across sensor modalities. We further demonstrate that the embeddings are stable over time as objects move around the scene. This not only provides stable instance masks, but can also provide valuable signals to downstream tasks, such as object tracking. We evaluate our method on the Cityscapes and KITTI-360 datasets. We further conduct a number of ablation studies, demonstrating benefits when applying additional inputs for the contrastive loss.

Event cameras provide a number of benefits over traditional cameras, such as the ability to track incredibly fast motions, high dynamic range, and low power consumption. However, their application into computer vision problems, many of which are primarily dominated by deep learning solutions, has been limited by the lack of labeled training data for events. In this work, we propose a method which leverages the existing labeled data for images by simulating events from a pair of temporal image frames, using a convolutional neural network. We train this network on pairs of images and events, using an adversarial discriminator loss and a pair of cycle consistency losses. The cycle consistency losses utilize a pair of pre-trained self-supervised networks which perform optical flow estimation and image reconstruction from events, and constrain our network to generate events which result in accurate outputs from both of these networks. Trained fully end to end, our network learns a generative model for events from images without the need for accurate modeling of the motion in the scene, exhibited by modeling based methods, while also implicitly modeling event noise. Using this simulator, we train a pair of downstream networks on object detection and 2D human pose estimation from events, using simulated data from large scale image datasets, and demonstrate the networks' abilities to generalize to datasets with real events. The code and dataset in this paper are available here: https://github.com/alexzzhu/EventGAN.

In this work, we propose a novel framework for unsupervised learning for event cameras that learns motion information from only the event stream. In particular, we propose an input representation of the events in the form of a discretized volume that maintains the temporal distribution of the events, which we pass through a neural network to predict the motion of the events. This motion is used to attempt to remove any motion blur in the event image. We then propose a loss function applied to the motion compensated event image that measures the motion blur in this image. We train two networks with this framework, one to predict optical flow, and one to predict egomotion and depths, and evaluate these networks on the Multi Vehicle Stereo Event Camera dataset, along with qualitative results from a variety of different scenes.

Event-based cameras are a novel asynchronous sensing modality that provide exciting benefits, such as the ability to track fast moving objects with no motion blur and low latency, high dynamic range, and low power consumption. Given the low latency of the cameras, as well as their ability to work in challenging lighting conditions, these cameras are a natural fit for reactive problems such as fast local structure estimation. In this work, we propose a fast method to perform structure estimation for vehicles traveling in a roughly 2D environment (e.g. in an environment with a ground plane). Our method transfers the method of plane and parallax to events, which, given the homography to a ground plane and the pose of the camera, generates a warping of the events which removes the optical flow for events on the ground plane, while inducing flow for events above the ground plane. We then estimate dense flow in this warped space using a self-supervised neural network, which provides the height of all points in the scene. We evaluate our method on the Multi Vehicle Stereo Event Camera dataset, and show its ability to rapidly estimate the scene structure both at high speeds and in low lighting conditions.

Event-based cameras provide a new visual sensing model by detecting changes in image intensity asynchronously across all pixels on the camera. By providing these events at extremely high rates (up to 1MHz), they allow for sensing in both high speed and high dynamic range situations where traditional cameras may fail. In this paper, we present the first algorithm to fuse a purely event-based tracking algorithm with an inertial measurement unit, to provide accurate metric tracking of a cameras full 6dof pose. Our algorithm is asynchronous, and provides measurement updates at a rate proportional to the camera velocity. The algorithm selects features in the image plane, and tracks spatiotemporal windows around these features within the event stream. An Extended Kalman Filter with a structureless measurement model then fuses the feature tracks with the output of the IMU. The camera poses from the filter are then used to initialize the next step of the tracker and reject failed tracks. We show that our method successfully tracks camera motion on the Event-Camera Dataset in a number of challenging situations.

Asynchronous event-based sensors present new challenges in basic robot vision problems like feature tracking. The few existing approaches rely on grouping events into models and computing optical flow after assigning future events to those models. Such a hard commitment in data association attenuates the optical flow quality and causes shorter flow tracks. In this paper, we introduce a novel soft data association modeled with probabilities. The association probabilities are computed in an intertwined EM scheme with the optical flow computation that maximizes the expectation (marginalization) over all associations. In addition, to enable longer tracks we compute the affine deformation with respect to the initial point and use the resulting residual as a measure of persistence. The computed optical flow enables a varying temporal integration different for every feature and sized inversely proportional to the length of the flow. We show results in egomotion and very fast vehicle sequences and we show the superiority over standard frame-based cameras.