Related papers: Connectivity-constrained Interactive Panoptic Segm…
The transformer-based semantic segmentation approaches, which divide the image into different regions by sliding windows and model the relation inside each window, have achieved outstanding success. However, since the relation modeling…
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…
Many deep learning based automated medical image segmentation systems, in reality, face difficulties in deployment due to the cost of massive data annotation and high latency in model iteration. We propose a dynamic interactive learning…
Visual actionable affordance has emerged as a transformative approach in robotics, focusing on perceiving interaction areas prior to manipulation. Traditional methods rely on pixel sampling to identify successful interaction samples or…
Click-point-based interactive segmentation has received widespread attention due to its efficiency. However, it's hard for existing algorithms to obtain precise and robust responses after multiple clicks. In this case, the segmentation…
Interactive segmentation enables clinicians to guide annotation, but existing zero-shot models like nnInteractive fail to consistently reach expert-level performance across diverse medical imaging tasks. Because annotation campaigns produce…
Moving object segmentation is critical to interpret scene dynamics for robotic navigation systems in challenging environments. Neuromorphic vision sensors are tailored for motion perception due to their asynchronous nature, high temporal…
Panoptic Narrative Grounding (PNG) is an emerging task whose goal is to segment visual objects of things and stuff categories described by dense narrative captions of a still image. The previous two-stage approach first extracts…
Dense pixel-wise classification maps output by deep neural networks are of extreme importance for scene understanding. However, these maps are often partially inaccurate due to a variety of possible factors. Therefore, we propose to…
Instance segmentation is one of the actively studied research topics in computer vision in which many objects of interest should be separated individually. While many feed-forward networks produce high-quality segmentation on different…
Most publicly available medical segmentation datasets are only partially labeled, with annotations provided for a subset of anatomical structures. When multiple datasets are combined for training, this incomplete annotation poses…
When one wants to train a neural network to perform semantic segmentation, creating pixel-level annotations for each of the images in the database is a tedious task. If he works with aerial or satellite images, which are usually very large,…
From the autonomous car driving to medical diagnosis, the requirement of the task of image segmentation is everywhere. Segmentation of an image is one of the indispensable tasks in computer vision. This task is comparatively complicated…
We investigate two optimization problems on area-proportional rectangle contact representations for layered, embedded planar graphs. The vertices are represented as interior-disjoint unit-height rectangles of prescribed widths, grouped in…
Deep learning-based techniques have proven effective in polyp segmentation tasks when provided with sufficient pixel-wise labeled data. However, the high cost of manual annotation has created a bottleneck for model generalization. To…
Inferring detailed 3D geometry of the scene is crucial for robotics applications, simulation, and 3D content creation. However, such information is hard to obtain, and thus very few datasets support it. In this paper, we propose an…
Graph neural networks (GNNs) have been widely applied in the recommendation tasks and have obtained very appealing performance. However, most GNN-based recommendation methods suffer from the problem of data sparsity in practice. Meanwhile,…
In current interactive instance segmentation works, the user is granted a free hand when providing clicks to segment an object; clicks are allowed on background pixels and other object instances far from the target object. This form of…
One popular approach to interactively segment the foreground object of interest from an image is to annotate a bounding box that covers the foreground object. Then, a binary labeling is performed to achieve a refined segmentation. One major…
Graphs are a useful abstraction of image content. Not only can graphs represent details about individual objects in a scene but they can capture the interactions between pairs of objects. We present a method for training a convolutional…