Results 11 to 20 of about 1,634,168 (383)
GLaMM: Pixel Grounding Large Multimodal Model [PDF]
Computer Vision and Pattern Recognition, 2023 Large Multimodal Models (LMMs) extend Large Lan-guage Models to the vision domain. Initial LMMs used holistic images and text prompts to generate ungrounded textual responses.
H. Rasheed +9 more
semanticscholar +1 more source
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization [PDF]
European Conference on Computer Vision, 2023 Diffusion models have demonstrated impressive performance in various image generation, editing, enhancement and translation tasks. In particular, the pre-trained text-to-image stable diffusion models provide a potential solution to the challenging ...
Tao Yang +3 more
semanticscholar +1 more source
PixelLM: Pixel Reasoning with Large Multimodal Model [PDF]
Computer Vision and Pattern Recognition, 2023 While large multimodal models (LMMs) have achieved remarkable progress, generating pixel-level masks for image reasoning tasks involving multiple open-world targets remains a challenge. To bridge this gap, we introduce PixelLM, an effective and efficient
Zhongwei Ren +6 more
semanticscholar +1 more source
Generalized Decoding for Pixel, Image, and Language [PDF]
Computer Vision and Pattern Recognition, 2022 We present X-Decoder, a generalized decoding model that can predict pixel-level segmentation and language tokens seamlessly. X-Decoder takes as input two types of queries: (i) generic non-semantic queries and (ii) semantic queries induced from text ...
Xueyan Zou +13 more
semanticscholar +1 more source
Pixel Difference Networks for Efficient Edge Detection [PDF]
IEEE International Conference on Computer Vision, 2021 Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities.
Z. Su +7 more
semanticscholar +1 more source
Exploring Cross-Image Pixel Contrast for Semantic Segmentation [PDF]
IEEE International Conference on Computer Vision, 2021 Current semantic segmentation methods focus only on mining "local" context, i.e., dependencies between pixels within individual images, by context-aggregation modules (e.g., dilated convolution, neural attention) or structure-aware optimization criteria (
Wenguan Wang +5 more
semanticscholar +1 more source
Osprey: Pixel Understanding with Visual Instruction Tuning [PDF]
Computer Vision and Pattern Recognition, 2023 Multimodal large language models (MLLMs) have recently achieved impressive general-purpose vision-language capabilities through visual instruction tuning.
Yuqian Yuan +7 more
semanticscholar +1 more source
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network [PDF]
Computer Vision and Pattern Recognition, 2016 Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input image is upscaled
Wenzhe Shi +7 more
semanticscholar +1 more source
One Pixel Attack for Fooling Deep Neural Networks [PDF]
IEEE Transactions on Evolutionary Computation, 2017 Recent research has revealed that the output of deep neural networks (DNNs) can be easily altered by adding relatively small perturbations to the input vector.
Jiawei Su +2 more
semanticscholar +1 more source
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization [PDF]
IEEE International Conference on Computer Vision, 2019 We introduce Pixel-aligned Implicit Function (PIFu), an implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object.
Shunsuke Saito +5 more
semanticscholar +1 more source