While a lot of recent efforts have been made on generalizing pose estimation to novel object instances within the same category, namely category-level 6D pose estimation, it is still restricted in constrained environments given the limited number of annotated data.

Transformers have revolutionized deep learning based computer vision with improved performance as well as robustness to natural corruptions and adversarial attacks. Transformers are used predominantly for 2D vision tasks, including image classification, semantic segmentation, and object detection. However, robots and advanced driver assistance systems also require 3D scene understanding for decision making by extracting structure-from-motion (SfM). We propose a robust transformer-based monocular SfM method that learns to predict monocular pixel-wise depth, ego vehicle's translation and rotation, as well as camera's focal length and principal point, simultaneously. With experiments on KITTI and DDAD datasets, we demonstrate how to adapt different vision transformers and compare them against contemporary CNN-based methods. Our study shows that transformer-based architecture, though lower in run-time efficiency, achieves comparable performance while being more robust against natural corruptions, as well as untargeted and targeted attacks.

Learning-based visual odometry (VO) algorithms achieve remarkable performance on common static scenes, benefiting from high-capacity models and massive annotated data, but tend to fail in dynamic, populated environments. Semantic segmentation is largely used to discard dynamic associations before estimating camera motions but at the cost of discarding static features and is hard to scale up to unseen categories. In this paper, we leverage the mutual dependence between camera ego-motion and motion segmentation and show that both can be jointly refined in a single learning-based framework. In particular, we present DytanVO, the first supervised learning-based VO method that deals with dynamic environments. It takes two consecutive monocular frames in real-time and predicts camera ego-motion in an iterative fashion. Our method achieves an average improvement of 27.7% in ATE over state-of-the-art VO solutions in real-world dynamic environments, and even performs competitively among dynamic visual SLAM systems which optimize the trajectory on the backend. Experiments on plentiful unseen environments also demonstrate our method's generalizability.

Advances in deep learning have resulted in steady progress in computer vision with improved accuracy on tasks such as object detection and semantic segmentation. Nevertheless, deep neural networks are vulnerable to adversarial attacks, thus presenting a challenge in reliable deployment. Two of the prominent tasks in 3D scene-understanding for robotics and advanced drive assistance systems are monocular depth and pose estimation, often learned together in an unsupervised manner. While studies evaluating the impact of adversarial attacks on monocular depth estimation exist, a systematic demonstration and analysis of adversarial perturbations against pose estimation are lacking. We show how additive imperceptible perturbations can not only change predictions to increase the trajectory drift but also catastrophically alter its geometry. We also study the relation between adversarial perturbations targeting monocular depth and pose estimation networks, as well as the transferability of perturbations to other networks with different architectures and losses. Our experiments show how the generated perturbations lead to notable errors in relative rotation and translation predictions and elucidate vulnerabilities of the networks.

Neural architecture search has proven to be highly effective in the design of computationally efficient, task-specific convolutional neural networks across several areas of computer vision. In 2D human pose estimation, however, its application has been limited by high computational demands. Hypothesizing that neural architecture search holds great potential for 2D human pose estimation, we propose a new weight transfer scheme that relaxes function-preserving mutations, enabling us to accelerate neuroevolution in a flexible manner. Our method produces 2D human pose network designs that are more efficient and more accurate than state-of-the-art hand-designed networks. In fact, the generated networks can process images at higher resolutions using less computation than previous networks at lower resolutions, permitting us to push the boundaries of 2D human pose estimation. Our baseline network designed using neuroevolution, which we refer to as EvoPose2D-S, provides comparable accuracy to SimpleBaseline while using 4.9x fewer floating-point operations and 13.5x fewer parameters. Our largest network, EvoPose2D-L, achieves new state-of-the-art accuracy on the Microsoft COCO Keypoints benchmark while using 2.0x fewer operations and 4.3x fewer parameters than its nearest competitor.

We describe a method to infer dense depth from camera motion and sparse depth as estimated using a visual-inertial odometry system. Unlike other scenarios using point clouds from lidar or structured light sensors, we have few hundreds to few thousand points, insufficient to inform the topology of the scene. Our method first constructs a piecewise planar scaffolding of the scene, and then uses it to infer dense depth using the image along with the sparse points. We use a predictive cross-modal criterion, akin to `self-supervision,' measuring photometric consistency across time, forward-backward pose consistency, and geometric compatibility with the sparse point cloud. We also launch the first visual-inertial + depth dataset, which we hope will foster additional exploration into combining the complementary strengths of visual and inertial sensors. To compare our method to prior work, we adopt the unsupervised KITTI depth completion benchmark, and show state-of-the-art performance on it.