Image Processing - Groups

WebCaricature dataset

The dataset used in the paper is the WebCaricature dataset, which contains 6,042 caricatures and 5,974 photographs from 252 persons.

Dataset
JSON

KITTI360

The KITTI360 dataset is used for evaluating the proposed Tuple-Circle loss function for cross-modality feature learning. The dataset consists of image and LiDAR scan pairs.

Dataset
JSON

MPI Sintel

The dataset used in the paper for unsupervised single image intrinsic decomposition.

Dataset
JSON

P3M-10k

Established the first large-scale anonymized portrait matting benchmark P3M-10k, containing 10,000 high-resolution face-blurred portrait images along with high-quality alpha...

Dataset
JSON

Stanford 2D3DS dataset

The Stanford 2D3DS dataset contains omni-directional images.

Dataset
JSON

OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matc...

Local feature matching is an essential component in many visual applications. In this work, we propose OAMatcher, a detector-free method that imitates humans behavior to realize...

Dataset
JSON

The Robustness Limits of SoTA Vision Models to Natural Variation

A dataset of more than 7 million images with controlled changes in pose, position, background, lighting color, and size.

Dataset
JSON

Middlebury

The Middlebury dataset is a benchmark for stereo vision and 3D reconstruction.

Dataset
JSON

Robustifying Vision Transformer without Retraining from Scratch

Vision Transformer (ViT) is becoming more popular in image processing. We investigate the effectiveness of test-time adaptation (TTA) on ViT, a technique that has emerged to...

Dataset
JSON

Photo Style Transfer Dataset

This dataset is used for photo style transfer.

Dataset
JSON

Rain100H

Synthetic rainy images dataset for training and testing the proposed LPNet for single image deraining.

Dataset
JSON

SPA-Data

The dataset for single image deraining, containing images with rain and their corresponding ground truth images.

Dataset
JSON

Binary Convolution Dataset

The dataset used in this paper is a binary convolution dataset, where the inputs are binary images and the outputs are the results of the convolution operation.

Dataset
JSON

Tursun et al.'s dataset

Tursun et al.'s dataset is used for testing the proposed HDR-Transformer.

Dataset
JSON

Sen et al.'s dataset

Sen et al.'s dataset is used for testing the proposed HDR-Transformer.

Dataset
JSON

Kalantari et al.'s dataset

Kalantari et al.'s dataset consists of 74 samples for training and 15 samples for testing.

Dataset
JSON

Subject2Vec: Generative-Discriminative Approach from a Set of Image Patches t...

A deep learning model that learns subject-level representation from a set of local features. The model represents the image volume as a bag (or set) of local features and can...

Dataset
JSON

Human Lips Dataset

The dataset used for testing the self-similarity-based super-resolution model for photoacoustic angiography.

Dataset
JSON

Mouse Brain Dataset

The dataset used for testing the self-similarity-based super-resolution model for photoacoustic angiography.

Dataset
JSON

Photoacoustic Angiography Images

The dataset used for training the self-similarity-based super-resolution model for photoacoustic angiography.

Dataset
JSON

148 datasets found