-
Scenenet RGB-D: 5M photorealistic images of synthetic indoor trajectories wit...
Scenenet RGB-D: 5M photorealistic images of synthetic indoor trajectories with ground truth -
MVSNeRF: Fast generalizable radiance field reconstruction from multi-view stereo
MVSNeRF: Fast generalizable radiance field reconstruction from multi-view stereo -
Multi-task view synthesis with Neural Radiance Fields
Multi-task view synthesis with neural radiance fields -
Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters
Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels... -
AWA2 (Animals with Attributes 2)
The AWA2 dataset includes 50 classes of assorted animals totaling 37,322 samples, of which 10 categories are considered unseen classes. Attribute annotations are 85-dimensional. -
SUN (SUN Attribute)
The SUN dataset has a sample of 717 different scenes totaling 14,340 images, where 72 categories are unseen classes. Attribute annotations are 102-dimensional. -
CUB (Caltech UCSD Birds 200)
The CUB dataset comprises 200 bird species totaling 11,788 image samples, of which 50 categories are planned as unseen classes. The SUN dataset has a sample of 717 different... -
Deep Geometric Moment (DGM) Model
The proposed model consists of three components: 1) Coordinate base computation: uses a 2D coordinate grid as input and generates the bases, 2) Image feature computation:... -
Improving Shape Awareness and Interpretability in Deep Networks Using Geometr...
Deep networks for image classification often rely more on texture information than object shape. This paper presents a deep-learning model inspired by geometric moments, a... -
Osteoarthritis Initiative (OAI) dataset
Knee OsteoArthritis (KOA) dataset used for early detection of KOA (KL-0 vs KL-2) using Vision Transformer (ViT) model with selective shuffled position embedding and key-patch... -
S3DIS and ShapeNetPart
The dataset used for indoor scene segmentation and object part segmentation. -
STL-10 dataset
The dataset used in this paper is a collection of images from the STL-10 dataset, preprocessed and used for training and evaluation of the proposed diffusion spectral entropy... -
Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction
We introduce Omni-LOS, a neural computational imaging method for conducting holistic shape reconstruction (HSR) of complex objects utilizing a Single-Photon Avalanche Diode... -
Graph-Regularized Attentive Convolutional Entanglement for Robust DeepFake Vi...
The proposed GRACE method leverages feature entanglement with sparse constraints and a graph convolutional network with graph Laplacian smoothing prior regularization to... -
Real-World Depth of Field Dataset
The dataset consists of real captured scenes with varying exposures, apertures, and focus distances. -
Cinematic Gaussians: Real-Time HDR Radiance Fields with Depth of Field
The dataset consists of four synthetic rendered scenes and four real captured scenes. The synthetic scenes provide control and ground truth for evaluation, while the real... -
Thumbnail Generation Dataset
Thumbnail generation dataset used in the paper for training and testing the proposed model. -
ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections
The proposed network architecture uses a threshold mechanism to further optimize the connection method, reducing connections between layers to accelerate inference time. -
Semantic Equitable Clustering: A Simple, Fast and Effective Strategy for Visi...
The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism’s quadratic complexity poses substantial...
