Related papers: High-Resolution Augmentation for Automatic Templat…

Parallel implementation of numerical adaptive mesh refinement (AMR)strategies for solving 3D elastostatic contact mechanics problems is an essential step toward complex simulations that exceed current performance levels. This paper…

Human Augmentation (HA) spans several technical fields and methodological approaches, including Experimental Psychology, Human-Computer Interaction, Psychophysiology, and Artificial Intelligence. Augmentation involves various strategies for…

We propose a general algorithm for non-conforming adaptive mesh refinement (AMR) of unstructured meshes in high-order finite element codes. Our focus is on h-refinement with a fixed polynomial order. The algorithm handles triangular,…

Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic…

Data augmentation methods inspired by CutMix have demonstrated significant potential in recent semi-supervised medical image segmentation tasks. However, these approaches often apply CutMix operations in a rigid and inflexible manner, while…

Self-supervised learning has become a cornerstone in various areas, particularly histopathological image analysis. Image augmentation plays a crucial role in self-supervised learning, as it generates variations in image samples. However,…

We propose a new learning method for heterogeneous domain adaptation (HDA), in which the data from the source domain and the target domain are represented by heterogeneous features with different dimensions. Using two different projection…

We introduce PHD, a novel approach for personalized 3D human mesh recovery (HMR) and body fitting that leverages user-specific shape information to improve pose estimation accuracy from videos. Traditional HMR methods are designed to be…

High dynamic range (HDR) imaging is of fundamental importance in modern digital photography pipelines and used to produce a high-quality photograph with well exposed regions despite varying illumination across the image. This is typically…

We propose a one-stage framework for real-time multi-person 3D human mesh estimation from a single RGB image. While current one-stage methods, which follow a DETR-style pipeline, achieve state-of-the-art (SOTA) performance with…

Data augmentation is an effective technique to improve the generalization of deep neural networks. Recently, AutoAugment proposed a well-designed search space and a search algorithm that automatically finds augmentation policies in a…

Deep neural networks are capable of learning powerful representations to tackle complex vision tasks but expose undesirable properties like the over-fitting issue. To this end, regularization techniques like image augmentation are necessary…

Analyzing high-dimensional data presents challenges due to the "curse of dimensionality'', making computations intensive. Dimension reduction techniques, categorized as linear or non-linear, simplify such data. Non-linear methods are…

In this paper, we propose a novel image interpolation algorithm, which is formulated via combining both the local autoregressive (AR) model and the nonlocal adaptive 3-D sparse model as regularized constraints under the regularization…

The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long videos or modeling intensive motions. Existing human image…

Humans use multiple communication channels to interact with each other. For instance, body gestures or facial expressions are commonly used to convey an intent. The use of such non-verbal cues has motivated the development of prediction…

Despite remarkable progress, existing multimodal large language models (MLLMs) are still inferior in granular visual recognition. Contrary to previous works, we study this problem from the perspective of image resolution, and reveal that a…

The recent surge in large-scale foundation models has spurred the development of efficient methods for adapting these models to various downstream tasks. Low-rank adaptation methods, such as LoRA, have gained significant attention due to…

Automatic data augmentation (AutoDA) plays an important role in enhancing the generalization of neural networks. However, mainstream AutoDA methods often encounter two challenges: either the search process is excessively time-consuming,…

This paper presents a novel framework to recover detailed human body shapes from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, and viewpoints. Prior methods typically attempt to…