In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method ...
Tons of images and videos are fed into machines for visual recognition a...
Although significant achievements have been achieved by recurrent neural...
As a highly ill-posed issue, single image super-resolution (SISR) has be...
Image super-resolution (SR) has been widely investigated in recent years...
Bit-depth expansion (BDE) is one of the emerging technologies to display...
Video prediction aims to predict future frames by modeling the complex
s...
Although many video prediction methods have obtained good performance in...
This paper introduces a novel Pre-trained Spatial Temporal Many-to-One
(...
It is challenging to restore low-resolution (LR) images to super-resolut...
Most of the existing 3D human pose estimation approaches mainly focus on...
End-to-end optimization capability offers neural image compression (NIC)...
Optimized for pixel fidelity metrics, images compressed by existing imag...
Cross-component linear model (CCLM) prediction has been repeatedly prove...
Face restoration is an inherently ill-posed problem, where additional pr...
Super-resolution is a classical issue in image restoration field. In rec...
Human pose transfer (HPT) is an emerging research topic with huge potent...
The ability to produce convincing textural details is essential for the
...
Single image super-resolution (SISR), as a traditional ill-conditioned
i...
Existing face restoration researches typically relies on either the
degr...
It plays a fundamental role to compactly represent the visual informatio...
As 3D scanning devices and depth sensors advance, dynamic point clouds h...
Existing captioning models often adopt the encoder-decoder architecture,...
Existing methods for image captioning are usually trained by cross entro...
In recent years, the image and video coding technologies have advanced b...
In this paper, we propose a scalable image compression scheme, including...
Light field (LF) representations aim to provide photo-realistic,
free-vi...
Deep learning has demonstrated tremendous break through in the area of
i...