A Dual-Augmentor Framework for Domain Generalization in 3D Human Pose Estimation
Abstract 3D human pose data collected in controlled laboratory settings present challenges
for pose estimators that generalize across diverse scenarios. To address this domain …
for pose estimators that generalize across diverse scenarios. To address this domain …
High-fidelity document stain removal via a large-scale real-world dataset and a memory-augmented transformer
Document images are often degraded by various stains, significantly impacting their
readability and hindering downstream applications such as document digitization and …
readability and hindering downstream applications such as document digitization and …
Smaformer: Synergistic multi-attention transformer for medical image segmentation
In medical image segmentation, specialized computer vision techniques, notably
transformers grounded in attention mechanisms and residual networks employing skip …
transformers grounded in attention mechanisms and residual networks employing skip …
Test-time intensity consistency adaptation for shadow detection
Shadow detection is crucial for accurate scene understanding in computer vision, yet it is
challenged by the diverse appearances of shadows caused by variations in illumination …
challenged by the diverse appearances of shadows caused by variations in illumination …
A survey on deep 3D human pose estimation
RB Neupane, K Li, TF Boka - Artificial Intelligence Review, 2024 - Springer
Abstract 3D Human Pose Estimation (3D-HPE) is a highly active and evolving research area
in computer vision with numerous applications such as extended reality, action recognition …
in computer vision with numerous applications such as extended reality, action recognition …
Uwformer: Underwater image enhancement via a semi-supervised multi-scale transformer
Underwater images often exhibit poor quality, distorted color balance and low contrast due
to the complex and intricate interplay of light, water, and objects. Despite the significant …
to the complex and intricate interplay of light, water, and objects. Despite the significant …
Learning to Manipulate Artistic Images
Recent advancement in computer vision has significantly lowered the barriers to artistic
creation. Exemplar-based image translation methods have attracted much attention due to …
creation. Exemplar-based image translation methods have attracted much attention due to …
PoseGen: Learning to Generate 3D Human Pose Dataset with NeRF
This paper proposes an end-to-end framework for generating 3D human pose datasets
using Neural Radiance Fields (NeRF). Public datasets generally have limited diversity in …
using Neural Radiance Fields (NeRF). Public datasets generally have limited diversity in …
An optimized-skeleton-based Parkinsonian gait auxiliary diagnosis method with both monitoring indicators and assisted ratings
Abnormal gait is one of the indispensable diagnostic sources of Parkinson's disease (PD)
diagnosis, typically presenting as small shuffling steps and gait bradykinesia. However, its …
diagnosis, typically presenting as small shuffling steps and gait bradykinesia. However, its …
Hierarchical Local Temporal Feature Enhancing for Transformer-Based 3D Human Pose Estimation
Recent advancements in transformer-based methods have yielded substantial success in
2D-to-3D human pose estimation. Transformer-based estimators have their inherent …
2D-to-3D human pose estimation. Transformer-based estimators have their inherent …