Related papers: Time-to-Label: Temporal Consistency for Self-Super…

Depth estimation and 3D object detection are critical for scene understanding but remain challenging to perform with a single image due to the loss of 3D information during image capture. Recent models using deep neural networks have…

We present MonoPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction. First, using the fundamental relations of a pinhole camera model, detections from a mature 2D object detector are used to generate…

Self-supervision provides effective representations for downstream tasks without requiring labels. However, existing approaches lag behind fully supervised training and are often not thought beneficial beyond obviating or reducing the need…

Time-series representation learning can extract representations from data with temporal dynamics and sparse labels. When labeled data are sparse but unlabeled data are abundant, contrastive learning, i.e., a framework to learn a latent…

Perceiving the physical world in 3D is fundamental for self-driving applications. Although temporal motion is an invaluable resource to human vision for detection, tracking, and depth perception, such features have not been thoroughly…

In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object…

Although cameras are ubiquitous, robotic platforms typically rely on active sensors like LiDAR for direct 3D perception. In this work, we propose a novel self-supervised monocular depth estimation method combining geometry with a new deep…

Understanding the geometry and pose of objects in 2D images is a fundamental necessity for a wide range of real world applications. Driven by deep neural networks, recent methods have brought significant improvements to object pose…

Monocular multi-object detection and localization in 3D space has been proven to be a challenging task. The MoNet3D algorithm is a novel and effective framework that can predict the 3D position of each object in a monocular image and draw a…

Directly learning multiple 3D objects motion from sequential images is difficult, while the geometric bundle adjustment lacks the ability to localize the invisible object centroid. To benefit from both the powerful object understanding…

Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at…

Temporal Activity Detection aims to predict activity classes per frame, in contrast to video-level predictions in Activity Classification (i.e., Activity Recognition). Due to the expensive frame-level annotations required for detection, the…

We study the problem of learning to estimate the 3D object pose from a few labelled examples and a collection of unlabelled data. Our main contribution is a learning framework, neural view synthesis and matching, that can transfer the 3D…

In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different…

Scene flow estimation has been receiving increasing attention for 3D environment perception. Monocular scene flow estimation -- obtaining 3D structure and 3D motion from two temporally consecutive images -- is a highly ill-posed problem,…

Estimating 3D hand pose directly from RGB imagesis challenging but has gained steady progress recently bytraining deep models with annotated 3D poses. Howeverannotating 3D poses is difficult and as such only a few 3Dhand pose datasets are…

Moving object segmentation is a crucial task for safe and reliable autonomous mobile systems like self-driving cars, improving the reliability and robustness of subsequent tasks like SLAM or path planning. While the segmentation of camera…

We propose a self-supervised approach for learning representations of objects from monocular videos and demonstrate it is particularly useful in situated settings such as robotics. The main contributions of this paper are: 1) a…

LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However,…

While unsupervised change detection using contrastive learning has been significantly improved the performance of literature techniques, at present, it only focuses on the bi-temporal change detection scenario. Previous state-of-the-art…