Related papers: Transformer-Based Model for Monocular Visual Odome…
This paper documents the winning entry at the CVPR2017 vehicle velocity estimation challenge. Velocity estimation is an emerging task in autonomous driving which has not yet been thoroughly explored. The goal is to estimate the relative…
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we…
For autonomous skill acquisition, robots have to learn about the physical rules governing the 3D world dynamics from their own past experience to predict and reason about plausible future outcomes. To this end, we propose a…
Visual Odometry (VO) is crucial for autonomous robotic navigation, especially in GPS-denied environments like planetary terrains. To improve robustness, recent model-based VO systems have begun combining standard and event-based cameras.…
Depth estimation has been widely studied and serves as the fundamental step of 3D perception for robotics and autonomous driving. Though significant progress has been made in monocular depth estimation in the past decades, these attempts…
Spatial scene-understanding, including dense depth and ego-motion estimation, is an important problem in computer vision for autonomous vehicles and advanced driver assistance systems. Thus, it is beneficial to design perception modules…
Monocular 3D object detection is an important task in autonomous driving. It can be easily intractable where there exists ego-car pose change w.r.t. ground plane. This is common due to the slight fluctuation of road smoothness and slope.…
Depth estimation is a fundamental knowledge for autonomous systems that need to assess their own state and perceive the surrounding environment. Deep learning algorithms for depth estimation have gained significant interest in recent years,…
Self-supervised learning for monocular depth estimation is widely investigated as an alternative to supervised learning approach, that requires a lot of ground truths. Previous works have successfully improved the accuracy of depth…
Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they…
While learning based depth estimation from images/videos has achieved substantial progress, there still exist intrinsic limitations. Supervised methods are limited by a small amount of ground truth or labeled data and unsupervised methods…
We address the problem of finding the current position and heading angle of an autonomous vehicle in real-time using a single camera. Compared to methods which require LiDARs and high definition (HD) 3D maps in real-time, the proposed…
Estimating rigid objects' poses is one of the fundamental problems in computer vision, with a range of applications across automation and augmented reality. Most existing approaches adopt one network per object class strategy, depend…
Optical Flow (OF) and depth are commonly used for visual odometry since they provide sufficient information about camera ego-motion in a rigid scene. We reformulate the problem of ego-motion estimation as a problem of motion estimation of a…
Odometry is of key importance for localization in the absence of a map. There is considerable work in the area of visual odometry (VO), and recent advances in deep learning have brought novel approaches to VO, which directly learn salient…
Learning to predict scene depth from RGB inputs is a challenging task both for indoor and outdoor robot navigation. In this work we address unsupervised learning of scene depth and robot ego-motion where supervision is provided by monocular…
We consider the problem of next frame prediction from video input. A recurrent convolutional neural network is trained to predict depth from monocular video input, which, along with the current video image and the camera trajectory, can…
Depth estimation is a core problem in robotic perception and vision tasks, but 3D reconstruction from a single image presents inherent uncertainties. Current depth estimation models primarily rely on inter-image relationships for supervised…
With the recent successful adaptation of transformers to the vision domain, particularly when trained in a self-supervised fashion, it has been shown that vision transformers can learn impressive object-reasoning-like behaviour and features…
Visual odometry (VO) is essential for enabling accurate point-goal navigation of embodied agents in indoor environments where GPS and compass sensors are unreliable and inaccurate. However, traditional VO methods face challenges in…