Tag
This paper proposes a feed-forward framework that decomposes 3D scenes into instance-structured token groups from unposed multi-view images, enabling direct object-level reconstruction, segmentation, and manipulation without 3D annotations.
YOLO26 is a multi-task computer vision model family released in January 2026, featuring end-to-end detection without Non-Maximum Suppression for lower latency and optimized for edge deployment with improved CPU inference and compact design.
Ultralytics YOLO26 introduces a unified real-time vision model family with NMS-free inference, improved training strategies, and multi-task capabilities for detection, segmentation, and pose estimation, achieving state-of-the-art accuracy-latency trade-offs.
This paper presents a vision-based pavement distress analysis system using Mask R-CNN instance segmentation, achieving high precision and recall for crack detection and quantification on a custom dataset.
Urban-ImageNet is a large-scale multi-modal dataset and evaluation benchmark for urban space perception from social media imagery, supporting scene classification, cross-modal retrieval, and instance segmentation tasks across 61 urban sites in 24 Chinese cities.