Talking Face Generation (TFG) aims to reconstruct facial movements to ac...
In this paper, we propose a novel network, SVDFormer, to tackle two spec...
Recall one time when we were in an unfamiliar mall. We might mistakenly ...
Rainy weather significantly deteriorates the visibility of scene objects...
Searching by image is popular yet still challenging due to the extensive...
Self-supervised learning is attracting large attention in point cloud
un...
Problems such as equipment defects or limited viewpoints will lead the
c...
Self-supervised learning is attracting wide attention in point cloud
pro...
What will happen when unsupervised learning meets diffusion models for
r...
There is a trend to fuse multi-modal information for 3D object detection...
Small targets are often submerged in cluttered backgrounds of infrared
i...
Image dehazing is fundamental yet not well-solved in computer vision. Mo...
Bilateral filter (BF) is a fast, lightweight and effective tool for imag...
We propose PSFormer, an effective point transformer model for 3D salient...
We propose GeoGCN, a novel geometric dual-domain graph convolution netwo...
How will you repair a physical object with large missings? You may first...
Adverse weather conditions such as haze, rain, and snow often impair the...
Image smoothing is a fundamental low-level vision task that aims to pres...
Mesh denoising is a fundamental problem in digital geometry processing. ...
Capturing both local and global features of irregular point clouds is
es...
The intricacy of 3D surfaces often results cutting-edge point cloud deno...
6D pose estimation of rigid objects from RGB-D images is crucial for obj...
High-confidence overlap prediction and accurate correspondences are crit...
How will you repair a physical object with some missings? You may imagin...
Low-overlap regions between paired point clouds make the captured featur...
This paper presents a novel deep neural network framework for RGB-D sali...
Convolution on 3D point clouds is widely researched yet far from perfect...
Snow is one of the toughest adverse weather conditions for object detect...
In recent years, Transformer models have been proven to have the remarka...
While the wisdom of training an image dehazing model on synthetic hazy d...
Rain is one of the most common weather which can completely degrade the ...
The intricacy of rainy image contents often leads cutting-edge deraining...
The shape of circle is one of fundamental geometric primitives of man-ma...
This paper studies a practically meaningful ship detection problem from
...
Point normal, as an intrinsic geometric property of 3D objects, not only...
Industrial bin picking is a challenging task that requires accurate and
...
Image filters are fast, lightweight and effective, which make these
conv...
Object detection has made tremendous strides in computer vision. Small o...
Low-light image enhancement (LLE) remains challenging due to the unfavor...
Convolution on 3D point clouds that generalized from 2D grid-like domain...
We present a novel direction-aware feature-level frequency decomposition...
Recently, the study on object detection in aerial images has made tremen...
Rain severely hampers the visibility of scene objects when images are
ca...
Image deraining is a fundamental, yet not well-solved problem in compute...
We propose a deep fully convolutional neural network with a new type of
...