In this paper, we present the decomposed triplane-hash neural radiance f...
Existing deep learning models for hyperspectral image (HSI) reconstructi...
Detailed 3D reconstruction and photo-realistic relighting of digital hum...
Domain adaptation of 3D portraits has gained more and more attention.
Ho...
In recent years, transformer-based detectors have demonstrated remarkabl...
When enhancing low-light images, many deep learning algorithms are based...
Multiple Instance Learning (MIL), a powerful strategy for weakly supervi...
Unsupervised representation learning for speech audios attained impressi...
The Transformer architecture model, based on self-attention and multi-he...
With the development of computational pathology, deep learning methods f...
The labels of monocular 3D object detection (M3OD) are expensive to obta...
How to properly model the inter-frame relation within the video sequence...
In coded aperture snapshot spectral compressive imaging (CASSI) systems,...
As an inherently ill-posed problem, depth estimation from single images ...
Existing leading methods for spectral reconstruction (SR) focus on desig...
Existing deep learning real denoising methods require a large amount of
...
Fast noninvasive probing of spatially varying decorrelating events, such...
Many algorithms have been developed to solve the inverse problem of code...
Light field disparity estimation is an essential task in computer vision...
The rapid development of deep learning provides a better solution for th...
Grapheme-to-phoneme (G2P) conversion is the process of converting the wr...
Exploiting similar and sharper scene patches in spatio-temporal neighbor...
Hyperspectral image (HSI) reconstruction aims to recover the 3D
spatial-...
Most existing video tasks related to "human" focus on the segmentation o...
Current methods of multi-person pose estimation typically treat the
loca...
Noninvasive optical imaging through dynamic scattering media has numerou...
Few-shot learning is challenging due to the limited data and labels. Exi...
In this paper, we propose a novel method called Residual Steps Network (...
Sparse representation (SR) and collaborative representation (CR) have be...
Image recognition is an important topic in computer vision and image
pro...
Retinex theory is developed mainly to decompose an image into the
illumi...
To overcome the oscillation problem in the classical momentum-based
opti...
The Reference-based Super-resolution (RefSR) super-resolves a low-resolu...
Specular reflection exists widely in photography and causes the recorded...