New method improves depth estimation for self-driving vehicles using only one image.
Gasser Elazab, Torben Gräber, Michael Unterreiner
― 5 min read
Computer Science - Computer Vision and Pattern Recognition
RSSSASS offers smart solutions for safer and better urban living.
Navid Salami Pargoo, Mahshid Ghasemi, Shuren Xia
― 6 min read
CogACT combines language and action for smarter robots in everyday tasks.
Qixiu Li, Yaobo Liang, Zeyu Wang
― 6 min read
A new approach makes multimodal models faster and more efficient.
Qiong Wu, Wenhao Lin, Weihao Ye
― 5 min read
Learn how TOrtho-Gaussian improves the creation of true digital maps.
Xin Wang, Wendi Zhang, Hong Xie
― 6 min read
FLD+ improves the evaluation of computer-generated images with fewer and more accurate measures.
Pranav Jeevan, Neeraj Nixon, Amit Sethi
― 5 min read
MulModSeg simplifies medical image segmentation for better diagnosis and treatment.
Chengyin Li, Hui Zhu, Rafi Ibn Sultan
― 5 min read
MotionPrompt improves video creation, ensuring smooth and consistent motion.
Hyelin Nam, Jaemin Kim, Dohun Lee
― 6 min read
SkelMamba improves movement analysis for healthcare using skeleton data.
Niki Martinel, Mariano Serrao, Christian Micheloni
― 6 min read
RAGDiffusion helps create realistic clothing images using advanced data gathering and image generation.
Xianfeng Tan, Yuhan Li, Wenxiang Shang
― 6 min read
Exploring quality assessments for 3D videos affected by environmental factors.
Sria Biswas, Balasubramanyam Appina, Priyanka Kokil
― 5 min read
Innovative methods improve data grouping with deep learning and K-means clustering.
Debapriya Roy
― 5 min read
A new approach for better AI understanding of images and text.
Jun Gao, Yongqi Li, Ziqiang Cao
― 6 min read
Sketch2Cinemagraph lets you create stunning animated images from simple drawings.
Hao Jin, Hengyuan Chang, Xiaoxuan Xie
― 7 min read
VideoSAVi changes how computers interpret videos through self-training.
Yogesh Kulkarni, Pooyan Fazli
― 8 min read
A new method improves how computers create 3D models from 2D images.
Chensheng Peng, Ido Sobol, Masayoshi Tomizuka
― 6 min read
ModPrompt helps object detectors adapt to new images effectively.
Heitor R. Medeiros, Atif Belal, Srikanth Muralidharan
― 6 min read
Advancing medical image translation for better diagnoses and patient care.
Anuja Vats, Ivar Farup, Marius Pedersen
― 7 min read
Transforming text prompts into realistic videos by incorporating physical laws.
Qiyao Xue, Xiangyu Yin, Boyuan Yang
― 6 min read
New techniques enhance 3D Gaussian Splatting for faster rendering.
Alex Hanson, Allen Tu, Geng Lin
― 5 min read
A fresh approach to improving image recovery without extensive training.
Michail Dontas, Yutong He, Naoki Murata
― 6 min read
New methods improve performance and efficiency in multimodal large language models.
Shiyu Zhao, Zhenting Wang, Felix Juefei-Xu
― 6 min read
A new system produces realistic videos with logical motion flows.
Tianshuo Xu, Zhifei Chen, Leyi Wu
― 8 min read
AI videos blur reality and deception, raising detection challenges.
Matyas Bohacek, Hany Farid
― 6 min read
New methods improve hyperspectral imaging for various real-world applications.
Chia-Ming Lee, Ching-Heng Cheng, Yu-Fan Lin
― 6 min read
Learn how new methods improve the recognition of small objects in 3D data.
Chade Li, Pengju Zhang, Yihong Wu
― 7 min read
LineGS improves 3D scene accuracy and efficiency through advanced line segments.
Chenggang Yang, Yuang Shi
― 6 min read
AgriBench evaluates AI tools to support smarter farming decisions.
Yutong Zhou, Masahiro Ryo
― 8 min read
FedGR improves federated learning by refining noisy labels for better collaboration.
Yuxin Tian, Mouxing Yang, Yuhao Zhou
― 6 min read
New AI methods enhance rainfall forecasting accuracy using satellite data.
Atharva Deshpande, Kaushik Gopalan, Jeet Shah
― 5 min read
TDAvec simplifies Topological Data Analysis for effective machine learning applications.
Aleksei Luchinsky, Umar Islambekov
― 7 min read
Discover how technology helps teachers measure student engagement in online classes.
Sharva Gogawale, Madhura Deshpande, Parteek Kumar
― 7 min read
New techniques improve gallbladder cancer detection using ultrasound images.
Chetan Madan, Mayuna Gupta, Soumen Basu
― 6 min read
AI technology improves brain tumor identification through advanced MRI analysis.
Sarim Hashmi, Juan Lugo, Abdelrahman Elsayed
― 9 min read
A new model enhances underwater images and identifies objects simultaneously.
Bin Li, Li Li, Zhenwei Zhang
― 7 min read
Learn how computers identify human emotions through facial expressions.
Dylan Waldner, Shyamal Mitra
― 6 min read
A new method boosts heart disease detection accuracy for better patient care.
Nourelhouda Groun, Maria Villalba-Orero, Lucia Casado-Martin
― 5 min read
New methods challenge traditional ground truth reliance in VSLAM and SfM technologies.
Alejandro Fontan, Javier Civera, Tobias Fischer
― 6 min read
A new approach to improve image-to-text descriptions.
Hao Wu, Zhihang Zhong, Xiao Sun
― 7 min read
Learn how M3-CVC improves video compression without losing quality.
Rui Wan, Qi Zheng, Yibo Fan
― 7 min read