Related papers: OPAL: Occlusion Pattern Aware Loss for Unsupervise…
Occluded face detection is a challenging detection task due to the large appearance variations incurred by various real-world occlusions. This paper introduces an Adversarial Occlusion-aware Face Detector (AOFD) by simultaneously detecting…
To overcome the problem of occlusion in visual tracking, this paper proposes an occlusion-aware tracking algorithm. The proposed algorithm divides the object into discrete image patches according to the pixel distribution of the object by…
This paper deals with the scarcity of data for training optical flow networks, highlighting the limitations of existing sources such as labeled synthetic datasets or unlabeled real videos. Specifically, we introduce a framework to generate…
Occlusion and the scarcity of labeled surgical data are significant challenges in disparity estimation for stereo laparoscopic images. To address these issues, this study proposes a Depth Guided Occlusion-Aware Disparity Refinement Network…
Depth perception is crucial for a wide range of robotic applications. Multi-frame self-supervised depth estimation methods have gained research interest due to their ability to leverage large-scale, unlabeled real-world data. However, the…
Optical approaches have made great strides towards the goal of high-speed, energy-efficient computing necessary for modern deep learning and AI applications. Read-in and read-out of data, however, limit the overall performance of existing…
We present an unsupervised simultaneous learning framework for the task of monocular camera re-localization and depth estimation from unlabeled video sequences. Monocular camera re-localization refers to the task of estimating the absolute…
Practical object pose estimation demands robustness against occlusions to the target object. State-of-the-art (SOTA) object pose estimators take a two-stage approach, where the first stage predicts 2D landmarks using a deep network and the…
We propose an end-to-end network that takes a single perspective RGB image of a complex road scene as input, to produce occlusion-reasoned layouts in perspective space as well as a parametric bird's-eye-view (BEV) space. In contrast to…
Machine learning has achieved much success on supervised learning tasks with large sets of well-annotated training samples. However, in many practical situations, such strong and high-quality supervision provided by training data is…
We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often…
Recently, convolutional networks (convnets) have proven useful for predicting optical flow. Much of this success is predicated on the availability of large datasets that require expensive and involved data acquisition and laborious la-…
Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an…
As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and quantifying image complexity remains a challenging task. (1)…
3D object detection based on monocular camera data is a key enabler for autonomous driving. The task however, is ill-posed due to lack of depth information in 2D images. Recent deep learning methods show promising results to recover depth…
Contrastive self-supervised learning has largely narrowed the gap to supervised pre-training on ImageNet. However, its success highly relies on the object-centric priors of ImageNet, i.e., different augmented views of the same image…
(Very early draft)Traditional supervised learning keeps pushing convolution neural network(CNN) achieving state-of-art performance. However, lack of large-scale annotation data is always a big problem due to the high cost of it, even…
Semantic segmentation models classify pixels into a set of known (``in-distribution'') visual classes. When deployed in an open world, the reliability of these models depends on their ability not only to classify in-distribution pixels but…
3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, leading to poor performance on unfamiliar scenes. We introduce…
Occlusion is an inevitable and critical problem in unsupervised optical flow learning. Existing methods either treat occlusions equally as non-occluded regions or simply remove them to avoid incorrectness. However, the occlusion regions can…