Related papers: WS-3D-Lane: Weakly Supervised 3D Lane Detection Wi…
Category-level 3D pose estimation is a fundamentally important problem in computer vision and robotics, e.g. for embodied agents or to train 3D generative models. However, so far methods that estimate the category-level object pose require…
With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…
Self-supervised learning has transformed 2D computer vision by enabling models trained on large, unannotated datasets to provide versatile off-the-shelf features that perform similarly to models trained with labels. However, in 3D scene…
Accurate 3D lane detection from monocular images presents significant challenges due to depth ambiguity and imperfect ground modeling. Previous attempts to model the ground have often used a planar ground assumption with limited degrees of…
Monocular 3D lane detection is challenged by aleatoric uncertainty arising from inherent observation noise. Existing methods rely on simplified geometric assumptions, such as independent point predictions or global planar modeling, failing…
3D lane detection from monocular images is a fundamental yet challenging task in autonomous driving. Recent advances primarily rely on structural 3D surrogates (e.g., bird's eye view) built from front-view image features and camera…
Fully-supervised monocular 3D hand reconstruction is often difficult because capturing the requisite 3D data entails deploying specialized equipment in a controlled environment. We introduce a weakly-supervised method that avoids such…
Semi- and weakly-supervised learning have recently attracted considerable attention in the object detection literature since they can alleviate the cost of annotation needed to successfully train deep learning models. State-of-art…
Current 3D object detection methods heavily rely on an enormous amount of annotations. Semi-supervised learning can be used to alleviate this issue. Previous semi-supervised 3D object detection methods directly follow the practice of…
Dense annotations, such as segmentation masks, are expensive and time-consuming to obtain, especially for 3D medical images where expert voxel-wise labeling is required. Weakly supervised approaches aim to address this limitation, but often…
Advanced Driver-Assistance Systems (ADAS) have successfully integrated learning-based techniques into vehicle perception and decision-making. However, their application in 3D lane detection for effective driving environment perception is…
Finding automatically multiple lesions in large images is a common problem in medical image analysis. Solving this problem can be challenging if, during optimization, the automated method cannot access information about the location of the…
Semi-supervised 3D object detection is a promising yet under-explored direction to reduce data annotation costs, especially for cluttered indoor scenes. A few prior works, such as SESS and 3DIoUMatch, attempt to solve this task by utilizing…
Despite the remarkable performance of supervised medical image segmentation models, relying on a large amount of labeled data is impractical in real-world situations. Semi-supervised learning approaches aim to alleviate this challenge using…
Frame-level micro- and macro-expression spotting methods require time-consuming frame-by-frame observation during annotation. Meanwhile, video-level spotting lacks sufficient information about the location and number of expressions during…
In this paper, we address the problem of road segmentation and free space detection in the context of autonomous driving. Traditional methods either use 3-dimensional (3D) cues such as point clouds obtained from LIDAR, RADAR or stereo…
We present Rewis3d, a framework that leverages recent advances in feed-forward 3D reconstruction to significantly improve weakly supervised semantic segmentation on 2D images. Obtaining dense, pixel-level annotations remains a costly…
Object detection is an import task of computer vision.A variety of methods have been proposed,but methods using the weak labels still do not have a satisfactory result.In this paper,we propose a new framework that using the weakly…
Background subtraction is a fundamental task in computer vision with numerous real-world applications, ranging from object tracking to video surveillance. Dynamic backgrounds poses a significant challenge here. Supervised deep…
Frame-by-frame annotation of bounding boxes by clinical experts is often required to train fully supervised object detection models on medical video data. We propose a method for improving object detection in medical videos through weak…