Results 1 to 10 of about 146,533 (343)
SUN RGB-D: A RGB-D scene understanding benchmark suite [PDF]
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015 Although RGB-D sensors have enabled major break-throughs for several vision tasks, such as 3D reconstruction, we have not attained the same level of success in high-level scene understanding. Perhaps one of the main reasons is the lack of a large-scale benchmark with 3D annotations and 3D evaluation metrics.
Shuran Song +2 more
semanticscholar +3 more sources
Person Re-Identification with RGB–D and RGB–IR Sensors: A Comprehensive Survey
Sensors, 2023 Learning about appearance embedding is of great importance for a variety of different computer-vision applications, which has prompted a surge in person re-identification (Re-ID) papers.
Md Kamal Uddin +4 more
doaj +3 more sources
NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM [PDF]
International Conference on 3D Vision, 2023 Neural implicit representations have recently become popular in simultaneous localization and mapping (SLAM), especially in dense visual SLAM. However, existing works either rely on RGB-D sensors or require a separate monocular SLAM approach for camera ...
Zihan Zhu +6 more
semanticscholar +1 more source
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation With Transformers [PDF]
IEEE transactions on intelligent transportation systems (Print), 2022 Scene understanding based on image segmentation is a crucial component of autonomous vehicles. Pixel-wise semantic segmentation of RGB images can be advanced by exploiting complementary features from the supplementary modality ( ${X}$ -modality). However,
Huayao Liu +4 more
semanticscholar +1 more source
Channel Exchanging for RGB-T Tracking [PDF]
Sensors, 2021 It is difficult to achieve all-weather visual object tracking in an open environment only utilizing single modality data input. Due to the complementarity of RGB and thermal infrared (TIR) data in various complex environments, a more robust object tracking framework can be obtained using video data of these two modalities. The fusion methods of RGB and
Long Zhao +3 more
openaire +4 more sources
Neural RGB-D Surface Reconstruction [PDF]
Computer Vision and Pattern Recognition, 2021 Obtaining high-quality 3D reconstructions of room-scale scenes is of paramount importance for upcoming applications in AR or VR. These range from mixed reality applications for teleconferencing, virtual measuring, virtual room planing, to robotic ...
Dejan Azinovi'c +4 more
semanticscholar +1 more source
SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection [PDF]
IEEE transactions on circuits and systems for video technology (Print), 2022 Convolutional neural networks (CNNs) are good at extracting contexture features within certain receptive fields, while transformers can model the global long-range dependency features.
Zhengyi Liu +3 more
semanticscholar +1 more source
Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images [PDF]
IEEE Transactions on Image Processing, 2022 Training deep models for RGB-D salient object detection (SOD) often requires a large number of labeled RGB-D images. However, RGB-D data is not easily acquired, which limits the development of RGB-D SOD techniques. To alleviate this issue, we present a Dual-Semi RGB-D Salient Object Detection Network (DS-Net) to leverage unlabeled RGB images for ...
Xiaoqiang Wang +7 more
openaire +4 more sources
Genetics of Germination and Seedling Traits under Drought Stress in a MAGIC Population of Maize
Plants, 2021 Drought is one of the most detrimental abiotic stresses hampering seed germination, development, and productivity. Maize is more sensitive to drought than other cereals, especially at seedling stage.
Soumeya Rida +5 more
doaj +1 more source
ANATOMY OF A CENOTE WITH USE OF DRON
Tropical and Subtropical Agroecosystems, 2021 Background: Detailed geomorphological analysis of the karst depressions in Yucatán has received little attention because the measurement of morphometric parameters taken in the field involves a lot of work, time and costs.
Gonzalo Neftaly Gijón-Yescas +3 more
doaj +1 more source