• Corpus ID: 244715019

High Quality Segmentation for Ultra High-resolution Images

  title={High Quality Segmentation for Ultra High-resolution Images},
  author={Tiancheng Shen and Yuecheng Zhang and Lu Qi and Jason Kuen and Xingyu Xie and Jianlong Wu and Zhe Lin and Jiaya Jia},
To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation. Common strategies, such as down-sampling, patch cropping, and cascade model, cannot address well the balance issue between accuracy and computation cost. Motivated by the fact that humans distinguish among objects continuously from coarse to precise levels, we propose the Continuous Refinement Model (CRM) for the ultra highresolution segmentation refinement task. CRM continuously aligns… 


Meticulous Object Segmentation
This paper proposes and studies a task named Meticulous Object Segmentation (MOS), which is focused on segmenting well-defined foreground objects with elaborate shapes in high resolution images, and proposes theMeticulousNet which leverages a dedicated decoder to capture the object boundary details.
CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
This paper presents quantitative and qualitative studies on different datasets to show that CascadePSP can reveal pixel-accurate segmentation boundaries using the novel refinement module without any finetuning.
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images
This work proposes collaborative Global-Local Networks (GLNet) to effectively preserve both global and local information in a highly memory-efficient manner, and achieves much more competitive accuracy-memory usage trade-offs compared to state-of-the-arts.
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
An image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address the challenging task of real-time semantic segmentation is proposed and in-depth analysis of the framework is provided.
PointRend: Image Segmentation As Rendering
The PointRend (Point-based Rendering) neural network module is presented: a module that performs point-based segmentation predictions at adaptively selected locations based on an iterative subdivision algorithm that enables output resolutions that are otherwise impractical in terms of memory or computation compared to existing approaches.
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner.
Rethinking Atrous Convolution for Semantic Image Segmentation
The proposed `DeepLabv3' system significantly improves over the previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.
Open-World Entity Segmentation
This work proposes a CondInst-like fully-convolutional architecture with two novel modules specifically designed to exploit the class-agnostic and non-overlapping requirements of ES, and investigates the feasibility of convolutional center-based representation to segment things and stuffs in a unified manner.
Hierarchical Image Saliency Detection on Extended CSSD
This work proposes a multi-layer approach and constructs an extended Complex Scene Saliency Dataset (ECSSD) to include complex but general natural images and improves detection quality on many images that cannot be handled well traditionally.
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF).