Sketch-based shape modeling aims to bridge the gap between 2D drawing an...
Recent work on Neural Radiance Fields (NeRF) has demonstrated significan...
Despite the rapid advancement of unsupervised learning in visual
represe...
In this paper, we introduce a realistic and challenging domain adaptatio...
In this paper, we tackle the challenging problem of 3D keypoint estimati...
High-quality data is essential for conversational recommendation systems...
Neural radiance fields (NeRF) have shown great success in novel view
syn...
Reconstructing dynamic 3D garment surfaces with open boundaries from
mon...
Virtual try-on attracts increasing research attention as a promising way...
3D shape completion from point clouds is a challenging task, especially ...
Extracting parametric edge curves from point clouds is a fundamental pro...
Assisting people in efficiently producing visually plausible 3D characte...
Neural radiance fields (NeRF) show great success in novel view synthesis...
Being data-driven is one of the most iconic properties of deep learning
...
In this work, we tackle the challenging problem of learning-based single...
Fast generation of high-quality 3D digital humans is important to a vast...
Radiance fields have gradually become a main representation of media.
Al...
Recently deep neural networks, which require a large amount of annotated...
Masked Modeling (MM) has demonstrated widespread success in various visi...
The mainstream of the existing approaches for video prediction builds up...
Holistic 3D scene understanding entails estimation of both layout
config...
Previous studies show the necessity of global and local adjustment for i...
We present a deep reinforcement learning method of progressive view
inpa...
It is very challenging to accurately reconstruct sophisticated human geo...
We present a new framework to reconstruct holistic 3D indoor scenes incl...
Domain Adaptive Object Detection (DAOD) focuses on improving the
general...
Semi-supervised domain adaptation (SSDA) aims to apply knowledge learned...
Automatic tooth instance segmentation on 3D dental models is a fundament...
In this paper, we revisit the verification of strong K-step opacity (K-S...
Fueled by the power of deep learning techniques and implicit shape learn...
Excellent performance has been achieved on instance segmentation but the...
Domain generalization (DG) aims to improve the generalization performanc...
For video frame interpolation (VFI), existing deep-learning-based approa...
Many basic indoor activities such as eating or writing are always conduc...
A key challenge of blind image super resolution is to recover realistic
...
Semantic segmentation of point cloud usually relies on dense annotation ...
We present PVSeRF, a learning framework that reconstructs neural radianc...
With wearable IMU sensors, one can estimate human poses from wearable de...
Long-range temporal alignment is critical yet challenging for video
rest...
Recent deep generative models allow real-time generation of hair images ...
Opacity, as an important property in information-flow security, characte...
Point completion refers to completing the missing geometries of an objec...
Head shapes play an important role in 3D character design. In this work,...
Despite video forecasting has been a widely explored topic in recent yea...
Fine-grained image recognition is challenging because discriminative clu...
Automatic segmentation of hepatocellular carcinoma (HCC)in Digital
Subtr...
Sampling, grouping, and aggregation are three important components in th...
Caricature is an artistic representation that deliberately exaggerates t...
Grounding referring expressions in RGBD image has been an emerging field...
Semantic scene understanding from point clouds is particularly challengi...