1,082 datasets found

Neural scene flow fields for space-time view synthesis of dynamic scenes.

Deformable Neural Radiance Fields extend NeRF by modeling non-rigidly deforming scenes.

A dataset of 10k images with artificially generated soiling patterns, used for training and testing the soiling detection model.

A companion dataset to the WoodScape dataset, containing 10k images with artificially generated soiling patterns.

The WoodScape dataset consists of 10,000 annotated images captured from four different view angles: Front View (FV), Mirror-View Right (MVR), Mirror-View Left (MVL), and Rear...

Labeled Faces in the Wild (LFW) dataset consists of 5749 subjects each having different number of images ranging from 1 to 530.

DiffPose: A conditional diffusion model for multi-hypothesis human pose estimation from a single image.

The dataset used in this paper for shadow detection, consisting of 4 widely used benchmark datasets: SBU, UCF, ISTD, and CUHK.

ExplainFix adopts two design principles: the “fixed filters” principle that all spatial filter weights of convolutional neural networks can be fixed at initialization and never...

A dataset for video generation and video-based tasks.

The proposed rectified binary convolutional networks (RBCNs) are used to improve the performance of 1-bit DCNNs for mobile and AI chips based applications.

This paper uses the ImageNet and COCO2017 validation datasets for testing.

The FastViT dataset is a fast vision transformer model.

The EdgeVITs dataset is a light-weight vision transformer model.

MobileViGv2 uses Mobile Graph Convolution (MGC) to demonstrate the effectiveness of our approach.

3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. PointConv can be applied on point clouds to build deep convolutional networks.

The YCB-Video dataset contains 92 videos of 21 objects with varying textures and sizes under cluttered indoor environments.

The LMO dataset is a subset of the LM dataset consisting of eight objects in more cluttered scenes.

The LM consists of 13 objects with approximately 1.2K images per object. We follow the settings described in [2], which uses 15% of the data for training and the rest for testing.

This dataset is used to evaluate the performance of a Convolutional Neural Network (CNN) on the ImageNet Large Scale Visual Recognition Challenge (ILSVRC2012).