Related papers: Improving Panoptic Segmentation at All Scales

Accurate weed management is essential for mitigating significant crop yield losses, necessitating effective weed suppression strategies in agricultural systems. Integrating cover crops (CC) offers multiple benefits, including soil erosion…

In precision agriculture, one of the most important tasks when exploring crop production is identifying individual plant components. There are several attempts to accomplish this task by the use of traditional 2D imaging, 3D…

We propose a novel optimization framework that crops a given image based on user description and aesthetics. Unlike existing image cropping methods, where one typically trains a deep network to regress to crop parameters or cropping…

Deep learning based image segmentation methods have achieved great success, even having human-level accuracy in some applications. However, due to the black box nature of deep learning, the best method may fail in some situations. Thus…

Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In contrast to prior work on unsupervised panoptic scene…

As deep learning-based computer vision algorithms continue to advance the state of the art, their robustness to real-world data continues to be an issue, making it difficult to bring an algorithm from the lab to the real world.…

Large-scale 3D point clouds can consist of hundreds of millions of points. Even after downsampling, these point clouds are too large for modern 3D neural networks. In order to develop a semantic understanding of the scene, the point clouds…

Panoptic segmentation aims to address semantic and instance segmentation simultaneously in a unified framework. However, an efficient solution of panoptic segmentation in applications like autonomous driving is still an open research…

The recently proposed panoptic segmentation task presents a significant challenge of image understanding with computer vision by unifying semantic segmentation and instance segmentation tasks. In this paper we present an efficient and novel…

In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by…

Lightweight and effective models are essential for devices with limited resources, such as intelligent vehicles. Structured pruning offers a promising approach to model compression and efficiency enhancement. However, existing methods often…

In the realm of autonomous mobile robots, safe navigation through unpaved outdoor environments remains a challenging task. Due to the high-dimensional nature of sensor data, extracting relevant information becomes a complex problem, which…

3D point cloud panoptic segmentation is the combined task to (i) assign each point to a semantic class and (ii) separate the points in each class into object instances. Recently there has been an increased interest in such comprehensive 3D…

The accuracy of mapping agricultural fields across large areas is steadily improving with high-resolution satellite imagery and deep learning (DL) models, even in regions where fields are small and geometrically irregular. However,…

3D part segmentation is an essential step in advanced CAM/CAD workflow. Precise 3D segmentation contributes to lower defective rate of work-pieces produced by the manufacturing equipment (such as computer controlled CNCs), thereby improving…

By benefiting from perceptual losses, recent studies have improved significantly the performance of the super-resolution task, where a high-resolution image is resolved from its low-resolution counterpart. Although such objective functions…

Most previous bounding-box-based segmentation methods assume the bounding box tightly covers the object of interest. However it is common that a rectangle input could be too large or too small. In this paper, we propose a novel segmentation…

Panoptic reconstruction is a challenging task in 3D scene understanding. However, most existing methods heavily rely on pre-trained semantic segmentation models and known 3D object bounding boxes for 3D panoptic segmentation, which is not…

Reliable LiDAR panoptic segmentation (LPS), including both semantic and instance segmentation, is vital for many robotic applications, such as autonomous driving. This work proposes a new LPS framework named PANet to eliminate the…

How to frame (or crop) a photo often depends on the image subject and its context; e.g., a human portrait. Recent works have defined the subject-aware image cropping task as a nuanced and practical version of image cropping. We propose a…