Suchergebnisse - grouping and shape analysis; Vision applications and systems

Image Segmentation Using Text and Image Prompts von Luddecke, Timo, Ecker, Alexander

“… Here we propose a system that can generate image segmentations based on arbitrary prompts at test time …”
Volltext

FocalClick: Towards Practical Interactive Image Segmentation von Chen, Xi, Zhao, Zhiyan, Zhang, Yilei, Duan, Manni, Qi, Donglian, Zhao, Hengshuang

“… Interactive segmentation allows users to extract target masks by making positive/negative clicks. Although explored by many previous works, there is still a …”
Volltext

Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation von Phan, Minh Hieu, Ta, The-Anh, Phung, Son Lam, Tran-Thanh, Long, Bouzerdoum, Abdesselam

“… Continual learning for semantic segmentation (CSS) is an emerging field in computer vision …”
Volltext

Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval von Bhunia, Ayan Kumar, Koley, Subhadeep, Khilji, Abdullah Faiz Ur Rahman, Sain, Aneeshan, Chowdhury, Pinaki Nath, Xiang, Tao, Song, Yi-Zhe

“… Sketching enables many exciting applications, notably, image retrieval. The fear-to-sketch problem (i.e., "I can't sketch …”
Volltext

LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network von Jiang, Zhigang, Xiang, Zhongzheng, Xu, Jinhua, Zhao, Ming

“… 3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient …”
Volltext

End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection von Li, Congcong, Wang, Xinyao, Wen, Longyin, Hong, Dexiang, Luo, Tiejian, Zhang, Libo

“… Generic event boundary detection aims to localize the generic, taxonomy-free event boundaries that segment videos into chunks. Existing methods typically …”
Volltext

A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation von Fazlali, Hamidreza, Xu, Yixuan, Ren, Yuan, Liu, Bingbing

“… 3D object detection using LiDAR data is an indispensable component for autonomous driving systems …”
Volltext

SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters von Mosella-Montoro, Albert, Ruiz-Hidalgo, Javier

“… on shape class and structure of the provided mesh. Whereas previous meth-ods pre-compute handcrafted features that relate the mesh and the skeleton or assume a fixed …”
Volltext

Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks von Lin, Fanqing, Price, Brian, Martinez, Tony

“… As deep neural networks become the state-of-the-art approach in the field of computer vision for dense prediction tasks, many methods have been developed for automatic estimation of the target outputs …”
Volltext

ADeLA: Automatic Dense Labeling with Attention for Viewpoint Shift in Semantic Segmentation von Ren, Hanxiang, Yang, Yanchao, Wang, He, Shen, Bokui, Fan, Qingnan, Zheng, Youyi, Liu, C. Karen, Guibas, Leonidas

“… We describe a method to deal with performance drop in semantic segmentation caused by viewpoint changes within multi-camera systems, where temporally paired images are readily available …”
Volltext

Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation von Li, Xiangtai, Zhang, Wenwei, Pang, Jiangmiao, Chen, Kai, Cheng, Guangliang, Tong, Yunhai, Loy, Chen Change

“… This paper presents Video K-Net, a simple, strong, and unified framework for fully end-to-end video panoptic seg-mentation. The method is built upon K-Net, a …”
Volltext

Finding Badly Drawn Bunnies von Yang, Lan, Pang, Kaiyue, Zhang, Honggang, Song, Yi-Zhe

“… As lovely as bunnies are, your sketched version would probably not do it justice (Fig. 1). This paper recognises this very problem and studies sketch quality …”
Volltext

Robust Histopathology Image Analysis: To Label or to Synthesize? von Hou, Le, Agarwal, Ayush, Samaras, Dimitris, Kurc, Tahsin M., Gupta, Rajarsi R., Saltz, Joel H.

“… Detection, segmentation and classification of nuclei are fundamental analysis operations in digital pathology …”
Volltext

BASNet: Boundary-Aware Salient Object Detection von Qin, Xuebin, Zhang, Zichen, Huang, Chenyang, Gao, Chao, Dehghan, Masood, Jagersand, Martin

“… Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works …”
Volltext

Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks von Fare Garnot, Vivien Sainte, Landrieu, Loic

“… Unprecedented access to multi-temporal satellite imagery has opened new perspectives for a variety of Earth observation tasks. Among them, pixel-precise …”
Volltext

Adaptive Pyramid Context Network for Semantic Segmentation von He, Junjun, Deng, Zhongying, Zhou, Lei, Wang, Yali, Qiao, Yu

“… Based on this analysis, this paper proposes Adaptive Pyramid Context Network (APCNet) for semantic segmentation …”
Volltext

Self-Supervised Shape Alignment for Sports Field Registration von Shi, Feng, Marchwica, Paul, Gamboa Higuera, Juan Camilo, Jamieson, Mike, Javan, Mehrsan, Siva, Parthipan

“… onto broadcast videos as a practical application. Rather then using any pairwise labelled data for training, we propose a self-supervised data mining method to train the registration network with a natural image and its edge map …”
Volltext

A Performance Evaluation of Correspondence Grouping Methods for 3D Rigid Data Matching von Yang, Jiaqi, Xian, Ke, Wang, Peng, Zhang, Yanning

“… ) is a fundamental problem in 3D computer vision. While a number of correspondence selection methods have been proposed in recent years, their advantages and shortcomings remain unclear regarding different applications and perturbations …”
Volltext

Deep Metric Learning for Open World Semantic Segmentation von Cen, Jun, Yun, Peng, Cai, Junhao, Yu Wang, Michael, Liu, Ming

“… ) objects, which is important for safety-critical applications such as autonomous driving …”
Volltext

Point Cloud Augmentation with Weighted Local Transformations von Kim, Sihyeon, Lee, Sanghyeok, Hwang, Dasol, Lee, Jaewon, Hwang, Seong Jae, Kim, Hyunwoo J.

“… Despite the extensive usage of point clouds in 3D vision, relatively limited data are available for training deep neural networks …”
Volltext