In this paper, we propose a novel framework, Tracking-free Relightable A...
In this paper, we tackle the challenging problem of 3D keypoint estimati...
In this work, we introduce a new approach for artistic face stylization....
Personalizing generative models offers a way to guide image generation w...
Given a 3D object, kinematic motion prediction aims to identify the mobi...
We present Unified Contrastive Arbitrary Style Transfer (UCAST), a novel...
In this work, we tackle the challenging problem of learning-based single...
An accurate understanding of omnidirectional environment lighting is cru...
The artistic style within a painting is the means of expression, which
i...
Despite the impressive results of arbitrary image-guided style transfer
...
In this work, we tackle the challenging problem of arbitrary image style...
In this paper, we tackle the challenging problem of point cloud completi...
In this paper, we tackle the problem of blind image super-resolution(SR)...
In this work, we present a new method for 3D face reconstruction from
mu...
In this paper, we introduce a brand new dataset to promote the study of
...
Developing deep neural networks to generate 3D scenes is a fundamental
p...
Sampling, grouping, and aggregation are three important components in th...
This paper introduces HPNet, a novel deep-learning approach for segmenti...
In this paper, we present D2C-SR, a novel framework for the task of imag...
In this paper, we introduce NBNet, a novel framework for image denoising...
Deep learning-based image denoising approaches have been extensively stu...
Video style transfer is getting more attention in AI community for its
n...
We introduce FPConv, a novel surface-style convolution operator designed...
We describe a policy learning approach to map visual inputs to driving
c...
In this work, we present a novel data-driven method for robust 6DoF obje...
Most previous image matting methods require a roughly-specificed trimap ...
In this paper we present a new data-driven method for robust skin detect...
In this paper, we present a new inpainting framework for recovering miss...
In this paper, we present new data pre-processing and augmentation techn...
Discriminative learning based image denoisers have achieved promising
pe...
Graphics Interchange Format (GIF) is a highly portable graphics format t...
Surface-based geodesic topology provides strong cues for object semantic...
Object functionality is often expressed through part articulation -- as ...
We present a new data-driven video inpainting method for recovering miss...
We introduce a large-scale 3D shape understanding benchmark using data a...
We propose a data-driven method for recovering miss-ing parts of 3D shap...
We present a new local descriptor for 3D shapes, directly applicable to ...