-
KITTI: A benchmark suite for computer vision tasks
KITTI: A benchmark suite for computer vision tasks. -
Texture vs Shape
This dataset is used to evaluate CNNs and human observers on images with a texture-shape cue conflict. -
One-shot Localization and Segmentation of Medical Images with Foundation Models
A variety of pre-trained ViT (DINO, DINOv2, SAM, CLIP) and SD models, trained exclusively on natural images, for solving the correspondence problems on medical images. -
Komaba Dataset
The Komaba dataset is a benchmark for LiDAR fusion. -
Non-learning Stereo-aided Depth Completion under Mis-projection via Selective...
The proposed method applies selective stereo matching (SSM) followed by binary anisotropic diffusion tensor (B-ADT) aided smoothing. -
ImageNet, MS COCO, Cityscapes, and ADE20K
The dataset used for the experiments in the paper, which includes ImageNet, MS COCO, Cityscapes, and ADE20K datasets. -
Argoverse Dataset
The Argoverse dataset is a large dataset of real-world outdoor driving scenes. -
Deep Automatic Portrait Matting
The dataset used for training and testing the proposed LSSC system, which consists of 1530 training images and 170 test images in RGB format. -
Text-to-Image Diffusion Models
The dataset used for text-to-image diffusion models, including Bluefire, Paintings, 3D, and Origami styles. -
Balanced Binary Neural Networks with Gated Residual
Binary neural networks have attracted numerous attention in recent years. However, mainly due to the information loss stemming from the biased binarization, how to preserve the... -
Visual Context-Aware Convolution Filters for Transformation-Invariant Neural ...
The proposed framework generates a unique set of context-dependent filters based on the input image, and combines them with max-pooling to produce transformation-invariant... -
KITTI and Ford Multi-AV Seasonal datasets
KITTI and Ford Multi-AV Seasonal datasets are used for training and evaluation of the proposed method. -
KITTI-CVL and FordAV-CVL datasets
Two cross-view localization datasets, KITTI-CVL and FordAV-CVL, are constructed by collecting spatial-consistent satellite counterparts from Google Map according to the provided... -
KITTI Benchmark Dataset
The KITTI benchmark dataset is used to evaluate the performance of the proposed method. The dataset contains large-scale outdoor sequences of images captured by a forward-facing... -
PartNetE Dataset
Constrained 6-DoF Grasp Generation on Complex Shapes for Improved Dual-Arm Manipulation -
ACRONYM Dataset
Constrained 6-DoF Grasp Generation on Complex Shapes for Improved Dual-Arm Manipulation -
DA2 Dataset
Constrained 6-DoF Grasp Generation on Complex Shapes for Improved Dual-Arm Manipulation