Depth estimation aims to predict dense depth maps. In autonomous driving...
Video depth estimation aims to infer temporally consistent depth. Some
m...
In an era where images and visual content dominate our digital landscape...
Recent portrait relighting methods have achieved realistic results of
po...
We present 3D Cinemagraphy, a new technique that marries 2D image animat...
Lighting effects such as shadows or reflections are key in making synthe...
Structure-guided image completion aims to inpaint a local region of an i...
Geometric camera calibration is often required for applications that
und...
Object compositing based on 2D images is a challenging problem since it
...
Developing a safe, stable, and efficient obstacle avoidance policy in cr...
Temporal consistency is the key challenge of video depth estimation. Pre...
Existing depth completion methods are often targeted at a specific spars...
Partial occlusion effects are a phenomenon that blurry objects near a ca...
We study the backward compatible problem for person re-identification
(R...
We propose BokehMe, a hybrid bokeh rendering framework that marries a ne...
Recent image inpainting methods have made great progress but often strug...
Despite the impressive representation capacity of vision transformer mod...
Image harmonization aims to improve the quality of image compositing by
...
We present a single-image data-driven method to automatically relight im...
Despite significant progress in monocular depth estimation in the wild,
...
We tackle the problem of semantic image layout manipulation, which aims ...
Compared with common image segmentation tasks targeted at low-resolution...
We propose Mask Guided (MG) Matting, a robust matting framework that tak...
Image compositing is a task of combining regions from different images t...
Modeling layout is an important first step for graphic design. Recently,...
While machine learning approaches to visual recognition offer great prom...
We propose a novel algorithm, named Open-Edit, which is the first attemp...
We present a novel resizing module for neural networks: shape adaptor, a...
In image compositing tasks, objects from different sources are put toget...
Existing image inpainting methods often produce artifacts when dealing w...
Conventionally, AI models are thought to trade off explainability for lo...
We introduce a novel framework for automatic capturing of human portrait...
Large scale object detection datasets are constantly increasing their si...
Deep neural network based methods have made a significant breakthrough i...
Deep models are state-of-the-art for many computer vision tasks includin...
Incremental learning targets at achieving good performance on new catego...
Layout is important for graphic design and scene generation. We propose ...
We propose Guided Zoom, an approach that utilizes spatial grounding to m...
In this paper, we study the problem of improving computational resource
...
We aim to generate high resolution shallow depth-of-field (DoF) images f...
We study the problem of learning a generalizable action policy for an
in...
Existing works on semantic segmentation typically consider a small numbe...
While machine learning approaches to visual emotion recognition offer gr...
We propose a guided dropout regularizer for deep networks based on the
e...
Deep models are state-of-the-art for many vision tasks including video a...
Neural image/video captioning models can generate accurate descriptions,...
We aim to model the top-down attention of a Convolutional Neural Network...
We study the problem of Salient Object Subitizing, i.e. predicting the
e...
Recently, attempts have been made to collect millions of videos to train...