相关论文: Self-Supervised 3D Keypoint Learning for Ego-motio…

Humans have impressive generalization capabilities when it comes to manipulating objects and tools in completely novel environments. These capabilities are, at least partially, a result of humans having internal models of their bodies and…

Learning depth and camera ego-motion from raw unlabeled RGB video streams is seeing exciting progress through self-supervision from strong geometric cues. To leverage not only appearance but also scene geometry, we propose a novel…

This paper introduces V-SysId, a novel method that enables simultaneous keypoint discovery, 3D system identification, and extrinsic camera calibration from an unlabeled video taken from a static camera, using only the family of equations of…

Lane detection has evolved highly functional autonomous driving system to understand driving scenes even under complex environments. In this paper, we work towards developing a generalized computer vision system able to detect lanes without…

Estimating camera wearer's body pose from an egocentric view (egopose) is a vital task in augmented and virtual reality. Existing approaches either use a narrow field of view front facing camera that barely captures the wearer, or an…

We propose a viewpoint invariant model for 3D human pose estimation from a single depth image. To achieve this, our discriminative model embeds local regions into a learned viewpoint invariant feature space. Formulated as a multi-task…

Unsupervised learning of depth and ego-motion from unlabelled monocular videos has recently drawn great attention, which avoids the use of expensive ground truth in the supervised one. It achieves this by using the photometric errors…

Successful visual navigation depends upon capturing images that contain sufficient useful information. In this letter, we explore a data-driven approach to account for environmental lighting changes, improving the quality of images for use…

Semantic 3D keypoints are category-level semantic consistent points on 3D objects. Detecting 3D semantic keypoints is a foundation for a number of 3D vision tasks but remains challenging, due to the ambiguity of semantic information,…

Supervised keypoint localization methods rely on large manually labeled image datasets, where objects can deform, articulate, or occlude. However, creating such large keypoint labels is time-consuming and costly, and is often error-prone…

We present a method for unsupervised learning of equations of motion for objects in raw and optionally distorted unlabeled video. We first train an autoencoder that maps each video frame into a low-dimensional latent space where the laws of…

This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single image, KeypointNet extracts 3D keypoints that are optimized…

We address the problem of depth and ego-motion estimation from image sequences. Recent advances in the domain propose to train a deep learning model for both tasks using image reconstruction in a self-supervised manner. We revise the…

This paper introduces KeyDiff3D, a framework for unsupervised monocular 3D keypoints estimation that accurately predicts 3D keypoints from a single image. While previous methods rely on manual annotations or calibrated multi-view images,…

This paper presents a new self-supervised system for learning to detect novel and previously unseen categories of objects in images. The proposed system receives as input several unlabeled videos of scenes containing various objects. The…

Predictive models have been at the core of many robotic systems, from quadrotors to walking robots. However, it has been challenging to develop and apply such models to practical robotic manipulation due to high-dimensional sensory…

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from…

We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen…

Inferring 3D human pose from 2D images is a challenging and long-standing problem in the field of computer vision with many applications including motion capture, virtual reality, surveillance or gait analysis for sports and medicine. We…

This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning. It roots from the observation that visual systems of human beings can easily identify video incoherence based on…