Instance Segmentation
Instance segmentation, a computer vision task, aims to identify and delineate individual objects within an image or point cloud, going beyond simple object detection by providing precise pixel-level masks. Current research emphasizes improving efficiency and accuracy, particularly in challenging scenarios like dense object arrangements, limited data, and noisy annotations; popular approaches involve transformer-based models, prototype-based methods, and techniques leveraging self-supervised learning or language-vision prompts. This field is crucial for diverse applications, including medical image analysis, autonomous driving, agricultural monitoring, and remote sensing, enabling automated analysis and improved decision-making in various domains.
Papers
Panoptica -- instance-wise evaluation of 3D semantic and instance segmentation maps
Florian Kofler, Hendrik Möller, Josef A. Buchner, Ezequiel de la Rosa, Ivan Ezhov, Marcel Rosier, Isra Mekki, Suprosanna Shit, Moritz Negwer, Rami Al-Maskari, Ali Ertürk, Shankeeth Vinayahalingam, Fabian Isensee, Sarthak Pati, Daniel Rueckert, Jan S. Kirschke, Stefan K. Ehrlich, Annika Reinke, Bjoern Menze, Benedikt Wiestler, Marie Piraud
PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation
Yuchen Zhou, Jiayuan Gu, Xuanlin Li, Minghua Liu, Yunhao Fang, Hao Su