Search
Search Results
-
Peridynamic differential operator for lossy compression and recovery of 3D point cloud data
This study presents a consistent mathematical framework to compress a densely populated 3D Point Cloud Data (PCD) set into a low-resolution subset of...
-
A Two-Stage Multi-domain Collaborative Optimization Network for 3D Human Mesh Recovery
3D human mesh recovery aims to reconstruct the 3D human mesh by estimating the 3D human mesh parameters in the video. Recent approaches mainly focus...
-
3D Hand Sequence Recovery from Real Blurry Images and Event Stream
Although hands frequently exhibit motion blur due to their dynamic nature, existing approaches for 3D hand recovery often disregard the impact of...
-
SMPL-IKS: A Mixed Analytical-Neural Inverse Kinematics Solver for 3D Human Mesh Recovery
We present SMPL-IKS, a mixed analytical-neural inverse kinematics solver that operates on the well-known Skinned Multi-Person Linear model (SMPL) to...
-
US-X Complete: A Multi-modal Approach to Anatomical 3D Shape Recovery
Ultrasound offers a radiation-free, cost-effective solution for real-time visualization of spinal landmarks, paraspinal soft tissues and...
-
3D Palmprint MCI Synthesis for 2D-3D Heterogeneous Palmprint Recognition
Cross-2D-to-3D (2D-3D) heterogeneous palmprint recognition aims to matching a 2D palmprint probe with the 3D palmprint galleries, which shows great...
-
3D-FaIR: 3D facial imperfection regeneration with defects by fully convolutional mesh autoencoder
This study introduces an effective approach using a fully convolutional mesh autoencoder model to reconstruct 3D facial features in the presence of...
-
Learning Dense UV Completion for 3D Human Mesh Recovery
Human mesh reconstruction from a single image is a challenging task due to the occlusion caused by self, objects, or other humans. Existing methods...
-
Multi-stage adaptive rank statistic pruning for lightweight human 3D mesh recovery model
We present a rank statistic adaptive multi-stage pruning method to find lightweight neural networks for 3D human mesh recovery while minimizing...
-
Single-Image 3D Human Pose and Shape Estimation Enhanced by Clothed 3D Human Reconstruction
3D human pose and shape estimation and clothed 3D human reconstruction are two hot topics in the community of computer vision. 3D human pose and...
-
Text-to-3D scene generation framework: bridging textual descriptions to high-fidelity 3D scenes
Text-to-3D scene generation is pivotal for digital content creation; however, existing methods often struggle with global consistency across views....
-
CMAE-3D: Contrastive Masked AutoEncoders for Self-Supervised 3D Object Detection
LiDAR-based 3D object detection is a crucial task for autonomous driving, owing to its accurate object recognition and localization capabilities in...
-
CLIP-Hand: CLIP-based regressor for hand pose estimation and mesh recovery
Despite significant advancements in 3D hand pose estimation, it still faces challenges due to self-occlusion and complex backgrounds. To tackle those...
-
Reversible data hiding in encrypted 3D mesh models via reference vertex circulation strategy
As information technology has quickly developed, many different industries have emerged along with it. Fields using 3D models as their fundamental...
-
HOOREX: Higher Order Optimizers for 3D Recovery from X-Ray Images
We propose a method to address the challenge of generating a 3D digital twin of a patient during an X-ray guided medical procedure from a single 2D...
-
3D Research Challenges in Cultural Heritage III Complexity and Quality in Digitisation
This open access book presents a collection of papers focusing on current 3D research challenges in the domain of digital cultural heritage. 3D...
-
3D-SELTML: stacking ensemble learning based on transformer meta-learner for 3D brain tumor segmentation
3D semantic brain tumor segmentation is a fundamental task in medical imaging and healthcare. It aims to automate and facilitate the labeling of...
-
A Survey of Recent Advances in Generative 3D Reconstruction
Inspired by the rapid progress of generative AI techniques, there have been huge advances made for the 3D (three-dimensional) reconstruction...
-
Single-view 3D reconstruction of surface of revolution
Symmetry prior on structure is instrumental for single-view 3D reconstruction. This paper introduces a novel mathematical approach for explicit...
-
Integration of BIM and Augmented Reality for the Recovery of Historical Built Heritage: A Research Perspective
Preserving historic built heritage imposes targeted interventions, combining recovery of historical structures with functional adaptation to...