SteeredMarigold improves depth maps, aiding robots in navigation and interaction.
Jakub Gregorek, Lazaros Nalpantidis
― 5 min read
Computer Science - Computer Vision and Pattern Recognition
RSSA new system improves drone efficiency in search and rescue operations.
Zhixi Cai, Cristian Rojas Cardenas, Kevin Leo
― 6 min read
ExelMap enhances the accuracy of HD map updates for safer autonomous driving.
Lena Wild, Ludvig Ericson, Rafael Valencia
― 5 min read
New techniques enhance robotic skills from simulations to real-world tasks.
Mohammad Nomaan Qureshi, Sparsh Garg, Francisco Yandun
― 5 min read
A new method offers improved 3D modeling from just one image, enhancing realism.
Peng Li, Wangguandong Zheng, Yuan Liu
― 7 min read
This study explores using Transfer Learning for effective quality control in CFRP tape laying.
Thomas Fraunholz, Dennis Rall, Tim Köhler
― 5 min read
MotionCom revolutionizes how objects are added to images dynamically.
Weijing Tao, Xiaofeng Yang, Miaomiao Cui
― 5 min read
New techniques enhance dynamic urban modeling for various applications.
Mahmud A. Mohamad, Gamal Elghazaly, Arthur Hubert
― 6 min read
SRIF enhances shape matching techniques for animation, 3D printing, and virtual reality.
Mingze Sun, Chen Guo, Puhua Jiang
― 6 min read
A new method enhances 3D scene clarity using 2D segmentation masks.
Joji Joseph, Bharadwaj Amrutur, Shalabh Bhatnagar
― 5 min read
Introducing GRIN, a new model for depth estimation using sparse data.
Vitor Guizilini, Pavel Tokmakov, Achal Dave
― 7 min read
AMD-MIL improves tissue analysis for faster and more accurate disease diagnosis.
Xitong Ling, Minxi Ouyang, Yizhi Wang
― 4 min read
A new method enhances sample selection in semi-supervised learning.
Qian Shao, Jiangrui Kang, Qiyuan Chen
― 4 min read
DAF-Net merges infrared and visible images for clearer insights.
Jian Xu, Xin He
― 5 min read
Robots can now use facial expressions to show pain, aiding in healthcare training.
Quang Tien Dam, Tri Tung Nguyen Nguyen, Dinh Tuan Tran
― 5 min read
VALO optimizes LiDAR detection for autonomous vehicles, balancing speed and accuracy.
Ahmet Soyyigit, Shuochao Yao, Heechul Yun
― 5 min read
NVLM enhances AI's grasp of language and visuals for diverse tasks.
Wenliang Dai, Nayeon Lee, Boxin Wang
― 5 min read
Using AI to improve early diagnosis of retinal diseases through enhanced imaging techniques.
Fatema-E- Jannat, Sina Gholami, Jennifer I. Lim
― 8 min read
RenderWorld uses visual data for safer self-driving technology.
Ziyang Yan, Wenzhen Dong, Yihua Shao
― 5 min read
OmniGen simplifies image creation tasks into a single model for all users.
Shitao Xiao, Yueze Wang, Junjie Zhou
― 5 min read
This work enhances CLIP's accuracy by addressing intra-modal overlap using lightweight adapters.
Alexey Kravets, Vinay Namboodiri
― 5 min read
LPT++ improves object recognition in classes with few examples through advanced techniques.
Bowen Dong, Pan Zhou, Wangmeng Zuo
― 6 min read
A new framework improves segmentation with limited examples.
Amirreza Fateh, Mohammad Reza Mohammadi, Mohammad Reza Jahed Motlagh
― 6 min read
A new approach enhances accuracy in aortic stenosis detection through machine learning.
Ang Nan Gu, Michael Tsang, Hooman Vaseli
― 6 min read
SLAck offers a new approach to tracking diverse objects in videos.
Siyuan Li, Lei Ke, Yung-Hsu Yang
― 6 min read
A benchmark for generalized few-shot segmentation in remote sensing is introduced.
Clifford Broni-Bediako, Junshi Xia, Jian Song
― 5 min read
A new method combines video, audio, and algorithms for better anomaly detection.
Yuta Kaneko, Abu Saleh Musa Miah, Najmul Hassan
― 7 min read
A look at Score Forgetting Distillation and its impact on generative AI.
Tianqi Chen, Shujian Zhang, Mingyuan Zhou
― 5 min read
SplatFields improves 3D imaging from limited camera views, boosting detail and quality.
Marko Mihajlovic, Sergey Prokudin, Siyu Tang
― 7 min read
Using synthetic data to enhance mobility tools for blind and low-vision individuals.
Hochul Hwang, Krisha Adhikari, Satya Shodhaka
― 6 min read
This article reviews the reliability of MIL models in clinical applications.
Hassan Keshvarikhojasteh
― 5 min read
A new method enhances pose estimation using RGB images informed by depth data.
Alessandro Simoni, Francesco Marchetti, Guido Borghi
― 6 min read
OneEncoder efficiently connects images, text, audio, and video for better information processing.
Bilal Faye, Hanane Azzag, Mustapha Lebbah
― 7 min read
New methods improve accuracy and efficiency in recognizing similar objects.
Edwin Arkel Rios, Femiloye Oyerinde, Min-Chun Hu
― 5 min read
Learn how to evaluate and compare images effectively.
Gautier Dagan, Olga Loginova, Anil Batra
― 4 min read
This model improves AI learning while retaining past knowledge.
Min-Yeong Park, Jae-Ho Lee, Gyeong-Moon Park
― 6 min read
A new system enhances safety predictions for autonomous vehicles in challenging environments.
Manthan Patel, Jonas Frey, Deegan Atha
― 6 min read
KALE uses metadata to generate insightful captions for artworks.
Yanbei Jiang, Krista A. Ehinger, Jey Han Lau
― 6 min read
TrajSSL enhances 3D object detection using fewer labeled data through motion forecasting.
Philip Jacobson, Yichen Xie, Mingyu Ding
― 6 min read
Exploring how LLMs improve reasoning across various data types.
Shengsheng Qian, Zuyi Zhou, Dizhan Xue
― 7 min read