Suchergebnisse - "Image Encoder/Decoder"

Potential Obstacle Detection Using RGB to Depth Image Encoder–Decoder Network: Application to Unmanned Aerial Vehicles

Autoren: Tomasz Hachaj

Quelle: Sensors, Vol 22, Iss 17, p 6703 (2022)

Schlagwörter: encoder–decoder network, depth prediction, RGB to depth mapping, obstacle detection, Unmanned Aerial Vehicles, deep neural network, Chemical technology, TP1-1185

Dateibeschreibung: electronic resource

Relation: https://www.mdpi.com/1424-8220/22/17/6703; https://doaj.org/toc/1424-8220

Zugangs-URL: https://doaj.org/article/7bbd297ade50496d8589b1b9a399ecd6

Dall-e Brain : Generation of 2D T1-w, T2-w, and FLAIR MRI images using a prompt

Autoren: El-Allaly, Souhail Breuil, Julie Bibard-Grau, Emma et al.

Weitere Verfasser: El-Allaly, Souhail Breuil, Julie Bibard-Grau, Emma et al.

Quelle: 3e édition du Colloque Français d'Intelligence Artificielle en Imagerie Biomédicale (IABM 2025).
https://hal.science/hal-05013997
3e édition du Colloque Français d'Intelligence Artificielle en Imagerie Biomédicale (IABM 2025)., Mar 2025, Nice, France

Schlagwörter: Registration, Image Encoder/Decoder, Variational AutoEncoder, Latent Diffusion Model, Text prompt conditioning, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-IM]Computer Science [cs]/Medical Imaging

Geographisches Schlagwort: Nice, France

Time: Nice, France

Verfügbarkeit: https://hal.science/hal-05013997
https://hal.science/hal-05013997v1/document
https://hal.science/hal-05013997v1/file/Poster_Dalle_Brain_IABM_TG_SE_vfi_3.pdf

Wavelet transformation-based image encoder, decoder and method for generating thumbnail image

Wavelet transformation-based image encoder, decoder and method for generating thumbnail image

Potential Obstacle Detection Using RGB to Depth Image Encoder–Decoder Network: Application to Unmanned Aerial Vehicles.

Autoren: Hachaj, Tomasz

Quelle: Sensors (14248220); Sep2022, Vol. 22 Issue 17, p6703, 15p

Schlagwörter: DRONE aircraft, AERIAL spraying & dusting in agriculture, ARTIFICIAL neural networks, DIGITAL cameras, SOURCE code, VIDEO coding

Method and device for the reduction of noise generated by a digital image encoder/decoder operating by blocks

Light Field Depth Estimation Method Based on Encoder-decoder Architecture

Autoren: YAN Xu MA Shuai ZENG Feng-jiao et al.

Quelle: Jisuanji kexue, Vol 48, Iss 10, Pp 212-219 (2021)

Schlagwörter: light field|depth estimation|epipolar plane image|encoder-decoder|context information, Computer software, QA76.75-76.765, Technology (General), T1-995

Relation: http://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2021-10-212.pdf; https://doaj.org/toc/1002-137X; https://doaj.org/article/db76123b20e145788ac32a57461b9709

Verfügbarkeit: https://doi.org/10.11896/jsjkx.200900005
https://doaj.org/article/db76123b20e145788ac32a57461b9709

Garment pattern generation method based on Diffusion Model and 3D reconstruction technology.

Autoren: Guo, Yuxuan Sun, Lin

Quelle: Textile Research Journal; Dec2025, Vol. 95 Issue 23/24, p2866-2881, 16p

Schlagwörter: PATTERN design (Clothing), FASHION design, CLOTHING industry, TEXTILE design, PATTERNMAKING, THREE-dimensional imaging, REVERSE engineering

Mamba-optimized transformer framework with dynamic deformation fields for real-time medical image registration.

Autoren: Jabbar, Muhammad Kashif Jianjun, Huang Jabbar, Ayesha et al.

Quelle: Journal of Big Data; 10/14/2025, Vol. 12 Issue 1, p1-32, 32p

Schlagwörter: IMAGE registration, TRANSFORMER models, SPATIAL resolution, MATHEMATICAL optimization, DEFORMATIONS (Mechanics), COMPUTER-assisted image analysis (Medicine), CONVOLUTIONAL neural networks

Consistent multimodal pre-training for visual tokenization.

Autoren: Pan, Ting Tang, Lulu Wang, Xinlong et al.

Quelle: SCIENCE CHINA Information Sciences; Oct2025, Vol. 68 Issue 10, p1-15, 15p

Deep learning steganography for big data security using squeeze and excitation with inception architectures.

Autoren: Issac, Bini M. Kumar, S. N. Zafar, Sherin et al.

Quelle: Scientific Reports; 8/25/2025, Vol. 15 Issue 1, p1-17, 17p

Schlagwörter: DEEP learning, INFORMATION technology security, DATA protection software, ARTIFICIAL neural networks, REAL-time computing, MEDICAL databases, CRYPTOGRAPHY

Deep learning applied for abnormal human behavior recognition in video surveillance systems: A systematic review.

Autoren: Saket, Olfa Aicha, Anis Ben Fathallah, Habib

Quelle: Applied Intelligence; Aug2025, Vol. 55 Issue 13, p1-25, 25p

融合全局-局部特征的低照度图像增强方法. (Chinese)

Alternate Title: Low Illumination Image Enhancement Method Integrating Global-Local Features. (English)

Autoren: 黄婷婷 曾上游 王靖

Quelle: Journal of Computer Engineering & Applications; Jul2025, Vol. 61 Issue 13, p321-328, 8p

Schlagwörter: IMAGE intensifiers, OPTICAL interference, VISUAL perception, SIGNAL-to-noise ratio, FEATURE extraction, IMAGE enhancement (Imaging systems)

Resource-efficient Algorithms and Systems of Foundation Models: A Survey.

Autoren: Xu, Mengwei Cai, Dongqi Yin, Wangsong et al.

Quelle: ACM Computing Surveys; May2025, Vol. 57 Issue 5, p1-39, 39p

Schlagwörter: ARTIFICIAL intelligence, ARTIFICIAL neural networks, GENERATIVE pre-trained transformers, LANGUAGE models, NATURAL language processing, CACHE memory, CHATBOTS

A multi-scale end-to-end visible and infrared image enhancement fusion method

Autoren: Yuanxue Xin Jiabin Huang Chao Sun et al.

CE-RoadNet: A Cascaded Efficient Road Network for Road Extraction from High-Resolution Satellite Images.

Autoren: Cheng, Ke-Nan Ni, Weiping Zhang, Han et al.

Quelle: Remote Sensing; Mar2025, Vol. 17 Issue 5, p831-1, 21p

Schlagwörter: REMOTE-sensing images, REMOTE sensing, URBAN planning, SIMPLICITY, NAVIGATION

Learning Models in Crowd Analysis: A Review.

Autoren: Goel, Silky Koundal, Deepika Nijhawan, Rahul

Quelle: Archives of Computational Methods in Engineering; Mar2025, Vol. 32 Issue 2, p943-961, 19p

Bridging the gap: multi-granularity representation learning for text-based vehicle retrieval.

Autoren: Bo, Xue Liu, Junjie Yang, Di et al.

Quelle: Complex & Intelligent Systems; Jan2025, Vol. 11 Issue 1, p1-12, 12p

Multiclass Image Segmentation using Deep Residual Encoder-Decoder Models in Highly Turbid Underwater Ambiances.

Autoren: Haridas, T. P. Mithun Kamal, Suraj Balakrishnan, Arun A. et al.

Quelle: International Journal of Mathematical, Engineering & Management Sciences; Dec2024, Vol. 9 Issue 6, p1510-1530, 21p

Schlagwörter: IMAGE segmentation, CORAL reefs & islands, UNDERWATER noise, CORALS, COST functions

A Review of Abnormal Crowd Behavior Recognition Technology Based on Computer Vision.

Autoren: Zhao, Rongyong Hua, Feng Wei, Bingyu et al.

Quelle: Applied Sciences (2076-3417); Nov2024, Vol. 14 Issue 21, p9758, 30p

Schlagwörter: COLLECTIVE behavior, COMPUTER vision, COMPUTER engineering, PUBLIC spaces, SOFTWARE development tools, DEEP learning