Punarjay Chakravarty

Cédric Picron, Punarjay Chakravarty, Tinne Tuytelaars

Recently, two-stage Deformable DETR introduced the query-based two-stage head, a new type of two-stage head different from the region-based two-stage heads of classical detectors as Faster R-CNN. In query-based two-stage heads, the second stage selects one feature per detection processed by a transformer, called the query, as opposed to pooling a rectangular grid of features processed by CNNs as in region-based detectors. In this work, we improve the query-based head by improving the prior of the cross-attention operation with anchors, significantly speeding up the convergence while increasing its performance. Additionally, we empirically show that by improving the cross-attention prior, auxiliary losses and iterative bounding box mechanisms typically used by DETR-based detectors are no longer needed. By combining the best of both the classical and the DETR-based detectors, our FQDet head peaks at 45.4 AP on the 2017 COCO validation set when using a ResNet-50+TPN backbone, only after training for 12 epochs using the 1x schedule. We outperform other high-performing two-stage heads such as e.g. Cascade R-CNN, while using the same backbone and while being computationally cheaper. Additionally, when using the large ResNeXt-101-DCN+TPN backbone and multi-scale testing, our FQDet head achieves 52.9 AP on the 2017 COCO test-dev set after only 12 epochs of training. Code is released at https://github.com/CedricPicron/FQDet .

Georgios Kouros, Shubham Shrivastava, Cédric Picron et al.

Pose estimation is usually tackled as either a bin classification or a regression problem. In both cases, the idea is to directly predict the pose of an object. This is a non-trivial task due to appearance variations between similar poses and similarities between dissimilar poses. Instead, we follow the key idea that comparing two poses is easier than directly predicting one. Render-and-compare approaches have been employed to that end, however, they tend to be unstable, computationally expensive, and slow for real-time applications. We propose doing category-level pose estimation by learning an alignment metric in an embedding space using a contrastive loss with a dynamic margin and a continuous pose-label space. For efficient inference, we use a simple real-time image retrieval scheme with a pre-rendered and pre-embedded reference set of renderings. To achieve robustness to real-world conditions, we employ synthetic occlusions, bounding box perturbations, and appearance augmentations. Our approach achieves state-of-the-art performance on PASCAL3D and OccludedPASCAL3D and surpasses the competing methods on KITTI3D in a cross-dataset evaluation setting. The code is currently available at https://github.com/gkouros/contrastive-pose-retrieval.

Georgios Kouros, Minye Wu, Shubham Shrivastava et al.

Neural Radiance Fields (NeRFs) have revolutionized the field of novel view synthesis, demonstrating remarkable performance. However, the modeling and rendering of reflective objects remain challenging problems. Recent methods have shown significant improvements over the baselines in handling reflective scenes, albeit at the expense of efficiency. In this work, we aim to strike a balance between efficiency and quality. To this end, we investigate an implicit-explicit approach based on conventional volume rendering to enhance the reconstruction quality and accelerate the training and rendering processes. We adopt an efficient density-based grid representation and reparameterize the reflected radiance in our pipeline. Our proposed reflection-aware approach achieves a competitive quality efficiency trade-off compared to competing methods. Based on our experimental results, we propose and discuss hypotheses regarding the factors influencing the results of density-based methods for reconstructing reflective objects. The source code is available at https://github.com/gkouros/ref-dvgo.

Zhengxia Zou, Rusheng Zhang, Shengyin Shen et al.

We propose a novel and pragmatic framework for traffic scene perception with roadside cameras. The proposed framework covers a full-stack of roadside perception pipeline for infrastructure-assisted autonomous driving, including object detection, object localization, object tracking, and multi-camera information fusion. Unlike previous vision-based perception frameworks rely upon depth offset or 3D annotation at training, we adopt a modular decoupling design and introduce a landmark-based 3D localization method, where the detection and localization can be well decoupled so that the model can be easily trained based on only 2D annotations. The proposed framework applies to either optical or thermal cameras with pinhole or fish-eye lenses. Our framework is deployed at a two-lane roundabout located at Ellsworth Rd. and State St., Ann Arbor, MI, USA, providing 7x24 real-time traffic flow monitoring and high-precision vehicle trajectory extraction. The whole system runs efficiently on a low-power edge computing device with all-component end-to-end delay of less than 20ms.

Stephen Hausler, Ming Xu, Sourav Garg et al.

6-DoF visual localization systems utilize principled approaches rooted in 3D geometry to perform accurate camera pose estimation of images to a map. Current techniques use hierarchical pipelines and learned 2D feature extractors to improve scalability and increase performance. However, despite gains in typical recall@0.25m type metrics, these systems still have limited utility for real-world applications like autonomous vehicles because of their `worst' areas of performance - the locations where they provide insufficient recall at a certain required error tolerance. Here we investigate the utility of using `place specific configurations', where a map is segmented into a number of places, each with its own configuration for modulating the pose estimation step, in this case selecting a camera within a multi-camera system. On the Ford AV benchmark dataset, we demonstrate substantially improved worst-case localization performance compared to using off-the-shelf pipelines - minimizing the percentage of the dataset which has low recall at a certain error tolerance, as well as improved overall localization performance. Our proposed approach is particularly applicable to the crowdsharing model of autonomous vehicle deployment, where a fleet of AVs are regularly traversing a known route.

Stephen Hausler, Sourav Garg, Punarjay Chakravarty et al.

Can knowing where you are assist in perceiving objects in your surroundings, especially under adverse weather and lighting conditions? In this work we investigate whether a prior map can be leveraged to aid in the detection of dynamic objects in a scene without the need for a 3D map or pixel-level map-query correspondences. We contribute an algorithm which refines an initial set of candidate object detections and produces a refined subset of highly accurate detections using a prior map. We begin by using visual place recognition (VPR) to retrieve a reference map image for a given query image, then use a binary classification neural network that compares the query and mapping image regions to validate the query detection. Once our classification network is trained, on approximately 1000 query-map image pairs, it is able to improve the performance of vehicle detection when combined with an existing off-the-shelf vehicle detector. We demonstrate our approach using standard datasets across two cities (Oxford and Zurich) under different settings of train-test separation of map-query traverse pairs. We further emphasize the performance gains of our approach against alternative design choices and show that VPR suffices for the task, eliminating the need for precise ground truth localization.

Sinnu Susan Thomas, Jacopo Palandri, Mohsen Lakehal-ayat et al.

Engineering design is traditionally performed by hand: an expert makes design proposals based on past experience, and these proposals are then tested for compliance with certain target specifications. Testing for compliance is performed first by computer simulation using what is called a discipline model. Such a model can be implemented by a finite element analysis, multibody systems approach, etc. Designs passing this simulation are then considered for physical prototyping. The overall process may take months, and is a significant cost in practice. We have developed a Bayesian optimization system for partially automating this process by directly optimizing compliance with the target specification with respect to the design parameters. The proposed method is a general framework for computing a generalized inverse of a high-dimensional non-linear function that does not require e.g. gradient information, which is often unavailable from discipline models. We furthermore develop a two-tier convergence criterion based on (i) convergence to a solution optimally satisfying all specified design criteria, or (ii) convergence to a minimum-norm solution. We demonstrate the proposed approach on a vehicle chassis design problem motivated by an industry setting using a state-of-the-art commercial discipline model. We show that the proposed approach is general, scalable, and efficient, and that the novel convergence criteria can be implemented straightforwardly based on existing concepts and subroutines in popular Bayesian optimization software packages.

Stephen Hausler, Sourav Garg, Punarjay Chakravarty et al.

Most 6-DoF localization and SLAM systems use static landmarks but ignore dynamic objects because they cannot be usefully incorporated into a typical pipeline. Where dynamic objects have been incorporated, typical approaches have attempted relatively sophisticated identification and localization of these objects, limiting their robustness or general utility. In this research, we propose a middle ground, demonstrated in the context of autonomous vehicles, using dynamic vehicles to provide limited pose constraint information in a 6-DoF frame-by-frame PnP-RANSAC localization pipeline. We refine initial pose estimates with a motion model and propose a method for calculating the predicted quality of future pose estimates, triggered based on whether or not the autonomous vehicle's motion is constrained by the relative frame-to-frame location of dynamic vehicles in the environment. Our approach detects and identifies suitable dynamic vehicles to define these pose constraints to modify a pose filter, resulting in improved recall across a range of localization tolerances from $0.25m$ to $5m$, compared to a state-of-the-art baseline single image PnP method and its vanilla pose filtering. Our constraint detection system is active for approximately $35\%$ of the time on the Ford AV dataset and localization is particularly improved when the constraint detection is active.

Yunfei Long, Daniel Morris, Xiaoming Liu et al.

While radar and video data can be readily fused at the detection level, fusing them at the pixel level is potentially more beneficial. This is also more challenging in part due to the sparsity of radar, but also because automotive radar beams are much wider than a typical pixel combined with a large baseline between camera and radar, which results in poor association between radar pixels and color pixel. A consequence is that depth completion methods designed for LiDAR and video fare poorly for radar and video. Here we propose a radar-to-pixel association stage which learns a mapping from radar returns to pixels. This mapping also serves to densify radar returns. Using this as a first stage, followed by a more traditional depth completion method, we are able to achieve image-guided depth completion with radar and video. We demonstrate performance superior to camera and radar alone on the nuScenes dataset. Our source code is available at https://github.com/longyunf/rc-pda.

Boris Ivanovic, Yifeng Lin, Shubham Shrivastava et al.

Uncertainty pervades through the modern robotic autonomy stack, with nearly every component (e.g., sensors, detection, classification, tracking, behavior prediction) producing continuous or discrete probabilistic distributions. Trajectory forecasting, in particular, is surrounded by uncertainty as its inputs are produced by (noisy) upstream perception and its outputs are predictions that are often probabilistic for use in downstream planning. However, most trajectory forecasting methods do not account for upstream uncertainty, instead taking only the most-likely values. As a result, perceptual uncertainties are not propagated through forecasting and predictions are frequently overconfident. To address this, we present a novel method for incorporating perceptual state uncertainty in trajectory forecasting, a key component of which is a new statistical distance-based loss function which encourages predicting uncertainties that better match upstream perception. We evaluate our approach both in illustrative simulations and on large-scale, real-world data, demonstrating its efficacy in propagating perceptual state uncertainty through prediction and producing more calibrated predictions.

Subodh Mishra, Armin Parchami, Enrique Corona et al.

This work presents a technique for localization of a smart infrastructure node, consisting of a fisheye camera, in a prior map. These cameras can detect objects that are outside the line of sight of the autonomous vehicles (AV) and send that information to AVs using V2X technology. However, in order for this information to be of any use to the AV, the detected objects should be provided in the reference frame of the prior map that the AV uses for its own navigation. Therefore, it is important to know the accurate pose of the infrastructure camera with respect to the prior map. Here we propose to solve this localization problem in two steps, \textit{(i)} we perform feature matching between perspective projection of fisheye image and bird's eye view (BEV) satellite imagery from the prior map to estimate an initial camera pose, \textit{(ii)} we refine the initialization by maximizing the Mutual Information (MI) between intensity of pixel values of fisheye image and reflectivity of 3D LiDAR points in the map data. We validate our method on simulated data and also present results with real world data.

Elijah S. Lee, Ankit Vora, Armin Parchami et al.

Vehicle localization is essential for autonomous vehicle (AV) navigation and Advanced Driver Assistance Systems (ADAS). Accurate vehicle localization is often achieved via expensive inertial navigation systems or by employing compute-intensive vision processing (LiDAR/camera) to augment the low-cost and noisy inertial sensors. Here we have developed a framework for fusing the information obtained from a smart infrastructure node (ix-node) with the autonomous vehicles on-board localization engine to estimate the robust and accurate pose of the ego-vehicle even with cheap inertial sensors. A smart ix-node is typically used to augment the perception capability of an autonomous vehicle, especially when the onboard perception sensors of AVs are blocked by the dynamic and static objects in the environment thereby making them ineffectual. In this work, we utilize this perception output from an ix-node to increase the localization accuracy of the AV. The fusion of ix-node perception output with the vehicle's low-cost inertial sensors allows us to perform reliable vehicle localization without the need for relying on expensive inertial navigation systems or compute-intensive vision processing onboard the AVs. The proposed approach has been tested on real-world datasets collected from a test track in Ann Arbor, Michigan. Detailed analysis of the experimental results shows that incorporating ix-node data improves localization performance.

Yunfei Long, Daniel Morris, Xiaoming Liu et al.

A distinctive feature of Doppler radar is the measurement of velocity in the radial direction for radar points. However, the missing tangential velocity component hampers object velocity estimation as well as temporal integration of radar sweeps in dynamic scenes. Recognizing that fusing camera with radar provides complementary information to radar, in this paper we present a closed-form solution for the point-wise, full-velocity estimate of Doppler returns using the corresponding optical flow from camera images. Additionally, we address the association problem between radar returns and camera images with a neural network that is trained to estimate radar-camera correspondences. Experimental results on the nuScenes dataset verify the validity of the method and show significant improvements over the state-of-the-art in velocity estimation and accumulation of radar points.

Mokshith Voodarla, Shubham Shrivastava, Sagar Manglani et al.

We describe a light-weight, weather and lighting invariant, Semantic Bird's Eye View (S-BEV) signature for vision-based vehicle re-localization. A topological map of S-BEV signatures is created during the first traversal of the route, which are used for coarse localization in subsequent route traversal. A fine-grained localizer is then trained to output the global 3-DoF pose of the vehicle using its S-BEV and its coarse localization. We conduct experiments on vKITTI2 virtual dataset and show the potential of the S-BEV to be robust to weather and lighting. We also demonstrate results with 2 vehicles on a 22 km long highway route in the Ford AV dataset.

Kaushik Balakrishnan, Punarjay Chakravarty, Shubham Shrivastava

Training robots to navigate diverse environments is a challenging problem as it involves the confluence of several different perception tasks such as mapping and localization, followed by optimal path-planning and control. Recently released photo-realistic simulators such as Habitat allow for the training of networks that output control actions directly from perception: agents use Deep Reinforcement Learning (DRL) to regress directly from the camera image to a control output in an end-to-end fashion. This is data-inefficient and can take several days to train on a GPU. Our paper tries to overcome this problem by separating the training of the perception and control neural nets and increasing the path complexity gradually using a curriculum approach. Specifically, a pre-trained twin Variational AutoEncoder (VAE) is used to compress RGBD (RGB & depth) sensing from an environment into a latent embedding, which is then used to train a DRL-based control policy. A*, a traditional path-planner is used as a guide for the policy and the distance between start and target locations is incrementally increased along the A* route, as training progresses. We demonstrate the efficacy of the proposed approach, both in terms of increased performance and decreased training times for the PointNav task in the Habitat simulation environment. This strategy of improving the training of direct-perception based DRL navigation policies is expected to hasten the deployment of robots of particular interest to industry such as co-bots on the factory floor and last-mile delivery robots.

Nithin Raghavan, Punarjay Chakravarty, Shubham Shrivastava

Image-based learning methods for autonomous vehicle perception tasks require large quantities of labelled, real data in order to properly train without overfitting, which can often be incredibly costly. While leveraging the power of simulated data can potentially aid in mitigating these costs, networks trained in the simulation domain usually fail to perform adequately when applied to images in the real domain. Recent advances in domain adaptation have indicated that a shared latent space assumption can help to bridge the gap between the simulation and real domains, allowing the transference of the predictive capabilities of a network from the simulation domain to the real domain. We demonstrate that a twin VAE-based architecture with a shared latent space and auxiliary decoders is able to bridge the sim2real gap without requiring any paired, ground-truth data in the real domain. Using only paired, ground-truth data in the simulation domain, this architecture has the potential to generate perception tasks such as depth and segmentation maps. We compare this method to networks trained in a supervised manner to indicate the merit of these results.

Cédric Picron, Punarjay Chakravarty, Tom Roussel et al.

The estimation of the orientation of an observed vehicle relative to an Autonomous Vehicle (AV) from monocular camera data is an important building block in estimating its 6 DoF pose. Current Deep Learning based solutions for placing a 3D bounding box around this observed vehicle are data hungry and do not generalize well. In this paper, we demonstrate the use of monocular visual odometry for the self-supervised fine-tuning of a model for orientation estimation pre-trained on a reference domain. Specifically, while transitioning from a virtual dataset (vKITTI) to nuScenes, we recover up to 70% of the performance of a fully supervised method. We subsequently demonstrate an optimization-based monocular 3D bounding box detector built on top of the self-supervised vehicle orientation estimator without the requirement of expensive labeled data. This allows 3D vehicle detection algorithms to be self-trained from large amounts of monocular camera data from existing commercial vehicle fleets.

Shubham Shrivastava, Punarjay Chakravarty

We introduce a method for 3D object detection using a single monocular image. Starting from a synthetic dataset, we pre-train an RGB-to-Depth Auto-Encoder (AE). The embedding learnt from this AE is then used to train a 3D Object Detector (3DOD) CNN which is used to regress the parameters of 3D object poses after the encoder from the AE generates a latent embedding from the RGB image. We show that we can pre-train the AE using paired RGB and depth images from simulation data once and subsequently only train the 3DOD network using real data, comprising of RGB images and 3D object pose labels (without the requirement of dense depth). Our 3DOD network utilizes a particular `cubification' of 3D space around the camera, where each cuboid is tasked with predicting N object poses, along with their class and confidence values. The AE pre-training and this method of dividing the 3D space around the camera into cuboids give our method its name - CubifAE-3D. We demonstrate results for monocular 3D object detection in the Autonomous Vehicle (AV) use-case with the Virtual KITTI 2 and the KITTI datasets.

Nikita Jaipuria, Xianling Zhang, Rohan Bhasin et al.

Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware. State-of-the-art methods for most vision tasks for Autonomous Vehicles (AVs) rely on supervised learning and often fail to generalize to domain shifts and/or outliers. Dataset diversity is thus key to successful real-world deployment. No matter how big the size of the dataset, capturing long tails of the distribution pertaining to task-specific environmental factors is impractical. The goal of this paper is to investigate the use of targeted synthetic data augmentation - combining the benefits of gaming engine simulations and sim2real style transfer techniques - for filling gaps in real datasets for vision tasks. Empirical studies on three different computer vision tasks of practical use to AVs - parking slot detection, lane detection and monocular depth estimation - consistently show that having synthetic data in the training mix provides a significant boost in cross-dataset generalization performance as compared to training on real data only, for the same size of the training set.

Tom Roussel, Punarjay Chakravarty, Gaurav Pandey et al.

We describe a Deep-Geometric Localizer that is able to estimate the full 6 Degree of Freedom (DoF) global pose of the camera from a single image in a previously mapped environment. Our map is a topo-metric one, with discrete topological nodes whose 6 DoF poses are known. Each topo-node in our map also comprises of a set of points, whose 2D features and 3D locations are stored as part of the mapping process. For the mapping phase, we utilise a stereo camera and a regular stereo visual SLAM pipeline. During the localization phase, we take a single camera image, localize it to a topological node using Deep Learning, and use a geometric algorithm (PnP) on the matched 2D features (and their 3D positions in the topo map) to determine the full 6 DoF globally consistent pose of the camera. Our method divorces the mapping and the localization algorithms and sensors (stereo and mono), and allows accurate 6 DoF pose estimation in a previously mapped environment using a single camera. With potential VR/AR and localization applications in single camera devices such as mobile phones and drones, our hybrid algorithm compares favourably with the fully Deep-Learning based Pose-Net that regresses pose from a single image in simulated as well as real environments.

Tim Salzmann, Boris Ivanovic, Punarjay Chakravarty et al.

Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation. As a result, multi-agent behavior prediction has become a core component of modern human-robot interactive systems, such as self-driving cars. While there exist many methods for trajectory forecasting, most do not enforce dynamic constraints and do not account for environmental information (e.g., maps). Towards this end, we present Trajectron++, a modular, graph-structured recurrent model that forecasts the trajectories of a general number of diverse agents while incorporating agent dynamics and heterogeneous data (e.g., semantic maps). Trajectron++ is designed to be tightly integrated with robotic planning and control frameworks; for example, it can produce predictions that are optionally conditioned on ego-agent motion plans. We demonstrate its performance on several challenging real-world trajectory forecasting datasets, outperforming a wide array of state-of-the-art deterministic and generative methods.

Praveen Narayanan, Punarjay Chakravarty, Francois Charette et al.

We present a voice conversion solution using recurrent sequence to sequence modeling for DNNs. Our solution takes advantage of recent advances in attention based modeling in the fields of Neural Machine Translation (NMT), Text-to-Speech (TTS) and Automatic Speech Recognition (ASR). The problem consists of converting between voices in a parallel setting when {\it $<$source,target$>$} audio pairs are available. Our seq2seq architecture makes use of a hierarchical encoder to summarize input audio frames. On the decoder side, we use an attention based architecture used in recent TTS works. Since there is a dearth of large multispeaker voice conversion databases needed for training DNNs, we resort to training the network with a large single speaker dataset as an autoencoder. This is then adapted for the smaller multispeaker voice conversion datasets available for voice conversion. In contrast with other voice conversion works that use $F_0$, duration and linguistic features, our system uses mel spectrograms as the audio representation. Output mel frames are converted back to audio using a wavenet vocoder.

Punarjay Chakravarty, Praveen Narayanan, Tom Roussel

We present a Deep Learning based system for the twin tasks of localization and obstacle avoidance essential to any mobile robot. Our system learns from conventional geometric SLAM, and outputs, using a single camera, the topological pose of the camera in an environment, and the depth map of obstacles around it. We use a CNN to localize in a topological map, and a conditional VAE to output depth for a camera image, conditional on this topological location estimation. We demonstrate the effectiveness of our monocular localization and depth estimation system on simulated and real datasets.

Rahaf Aljundi, Punarjay Chakravarty, Tinne Tuytelaars

In this work, we aim at automatically labeling actors in a TV series. Rather than relying on transcripts and subtitles, as has been demonstrated in the past, we show how to achieve this goal starting from a set of example images of each of the main actors involved, collected from the Internet Movie Database (IMDB). The problem then becomes one of domain adaptation: actors' IMDB photos are typically taken at awards ceremonies and are quite different from their appearances in TV series. In each series as well, there is considerable change in actor appearance due to makeup, lighting, ageing, etc. To bridge this gap, we propose a graph-matching based self-labelling algorithm, which we coin HSL (Hungarian Self Labeling). Further, we propose a new edge cost to be used in this context, as well as an extension that is more robust to outliers, where prototypical faces for each of the actors are selected based on a hierarchical clustering procedure. We conduct experiments with 15 episodes from 3 different TV series and demonstrate automatic annotation with an accuracy of 90% and up.

Rahaf Aljundi, Punarjay Chakravarty, Tinne Tuytelaars

In this paper we introduce a model of lifelong learning, based on a Network of Experts. New tasks / experts are learned and added to the model sequentially, building on what was learned before. To ensure scalability of this process,data from previous tasks cannot be stored and hence is not available when learning a new task. A critical issue in such context, not addressed in the literature so far, relates to the decision which expert to deploy at test time. We introduce a set of gating autoencoders that learn a representation for the task at hand, and, at test time, automatically forward the test sample to the relevant expert. This also brings memory efficiency as only one expert network has to be loaded into memory at any given time. Further, the autoencoders inherently capture the relatedness of one task to another, based on which the most relevant prior model to be used for training a new expert, with finetuning or learning without-forgetting, can be selected. We evaluate our method on image classification and video prediction problems.

Punarjay Chakravarty, Tinne Tuytelaars

In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based classifier in a weakly supervised manner. The classifier uses spatio-temporal features to encode upper body motion - facial expressions and gesticulations associated with speaking. We further improve a generic model for active speaker detection by learning person specific models. Finally, we demonstrate the online adaptation of generic models learnt on one dataset, to previously unseen people in a new dataset, again using audio (VAD) for weak supervision. The use of temporal continuity overcomes the lack of clean training data. We are the first to present an active speaker detection system that learns on one audio-visual dataset and automatically adapts to speakers in a new dataset. This work can be seen as an example of how the availability of multi-modal data allows us to learn a model without the need for supervision, by transferring knowledge from one modality to another.