NTIRE 2024 challenge on blind enhancement of compressed image: Methods and results
This paper reviews the Challenge on Blind Enhancement of Compressed Image at NTIRE
2024 which aims at enhancing the quality of JPEG images which are compressed with …
2024 which aims at enhancing the quality of JPEG images which are compressed with …
Recent advances on image edge detection: A comprehensive review
Edge detection is one of the most important and fundamental problems in the field of
computer vision and image processing. Edge contours extracted from images are widely …
computer vision and image processing. Edge contours extracted from images are widely …
Segment anything
Abstract We introduce the Segment Anything (SA) project: a new task, model, and dataset for
image segmentation. Using our efficient model in a data collection loop, we built the largest …
image segmentation. Using our efficient model in a data collection loop, we built the largest …
Scaling open-vocabulary image segmentation with image-level labels
We design an open-vocabulary image segmentation model to organize an image into
meaningful regions indicated by arbitrary texts. Recent works (CLIP and ALIGN), despite …
meaningful regions indicated by arbitrary texts. Recent works (CLIP and ALIGN), despite …
Repvit: Revisiting mobile cnn from vit perspective
Abstract Recently lightweight Vision Transformers (ViTs) demonstrate superior performance
and lower latency compared with lightweight Convolutional Neural Networks (CNNs) on …
and lower latency compared with lightweight Convolutional Neural Networks (CNNs) on …
Decoupling zero-shot semantic segmentation
Zero-shot semantic segmentation (ZS3) aims to segment the novel categories that have not
been seen in the training. Existing works formulate ZS3 as a pixel-level zero-shot …
been seen in the training. Existing works formulate ZS3 as a pixel-level zero-shot …
Pixel difference networks for efficient edge detection
Abstract Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level
performance in edge detection with the rich and abstract edge representation capacities …
performance in edge detection with the rich and abstract edge representation capacities …
Image de-raining transformer
Existing deep learning based de-raining approaches have resorted to the convolutional
architectures. However, the intrinsic limitations of convolution, including local receptive fields …
architectures. However, the intrinsic limitations of convolution, including local receptive fields …
Semantic-sam: Segment and recognize anything at any granularity
In this paper, we introduce Semantic-SAM, a universal image segmentation model to enable
segment and recognize anything at any desired granularity. Our model offers two key …
segment and recognize anything at any desired granularity. Our model offers two key …
Edter: Edge detection with transformer
Convolutional neural networks have made significant progresses in edge detection by
progressively exploring the context and semantic features. However, local details are …
progressively exploring the context and semantic features. However, local details are …