Bojian Wu
YOU?
Author Swipe
View article: NoPe‐NeRF++: Local‐to‐Global Optimization of NeRF with No Pose Prior
NoPe‐NeRF++: Local‐to‐Global Optimization of NeRF with No Pose Prior Open
In this paper, we introduce NoPe‐NeRF++, a novel local‐to‐global optimization algorithm for training Neural Radiance Fields (NeRF) without requiring pose priors. Existing methods, particularly NoPe‐NeRF, which focus solely on the local rel…
View article: Glossy Object Reconstruction with Cost-effective Polarized Acquisition
Glossy Object Reconstruction with Cost-effective Polarized Acquisition Open
The challenge of image-based 3D reconstruction for glossy objects lies in separating diffuse and specular components on glossy surfaces from captured images, a task complicated by the ambiguity in discerning lighting conditions and materia…
View article: VF-Plan: Bridging the Art Gallery Problem and Static LiDAR Scanning with Visibility Field Optimization
VF-Plan: Bridging the Art Gallery Problem and Static LiDAR Scanning with Visibility Field Optimization Open
Viewpoint planning is critical for efficient 3D data acquisition in applications such as 3D reconstruction, building life-cycle management, navigation, and interior decoration. However, existing methods often neglect key optimization objec…
View article: CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery
CoL3D: Collaborative Learning of Single-view Depth and Camera Intrinsics for Metric 3D Shape Recovery Open
Recovering the metric 3D shape from a single image is particularly relevant for robotics and embodied intelligence applications, where accurate spatial understanding is crucial for navigation and interaction with environments. Usually, the…
View article: PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration
PTZ-Calib: Robust Pan-Tilt-Zoom Camera Calibration Open
In this paper, we present PTZ-Calib, a robust two-stage PTZ camera calibration method, that efficiently and accurately estimates camera parameters for arbitrary viewpoints. Our method includes an offline and an online stage. In the offline…
View article: Learning Neural Volumetric Pose Features for Camera Localization
Learning Neural Volumetric Pose Features for Camera Localization Open
We introduce a novel neural volumetric pose feature, termed PoseMap, designed to enhance camera localization by encapsulating the information between images and the associated camera poses. Our framework leverages an Absolute Pose Regressi…
View article: The Ground Test System of Double Layer Air Floating Platform and Its Application
The Ground Test System of Double Layer Air Floating Platform and Its Application Open
The suspension test system within the high microgravity scientific experiment cabinet is equipped with double-layer vibration isolation, effectively isolating external disturbances and creating a high microgravity environment within the in…
View article: A micro-force measurement torsion pendulum design with dual laser detection
A micro-force measurement torsion pendulum design with dual laser detection Open
Aiming at the ground test and evaluation of the suspended test bench of the high microgravity scientific experiment cabinet in the Tianhe core module of the space station to obtain its exact thrust resolution, a micro-force measurement tor…
View article: Homography Loss for Monocular 3D Object Detection
Homography Loss for Monocular 3D Object Detection Open
Monocular 3D object detection is an essential task in autonomous driving. However, most current methods consider each 3D object in the scene as an independent training sample, while ignoring their inherent geometric relations, thus inevita…
View article: Intuitive and efficient roof modeling for reconstruction and synthesis
Intuitive and efficient roof modeling for reconstruction and synthesis Open
We propose a novel and flexible roof modeling approach that can be used for constructing planar 3D polygon roof meshes. Our method uses a graph structure to encode roof topology and enforces the roof validity by optimizing a simple but eff…
View article: Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis
Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis Open
We propose a novel and flexible roof modeling approach that can be used for constructing planar 3D polygon roof meshes. Our method uses a graph structure to encode roof topology and enforces the roof validity by optimizing a simple but eff…
View article: Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words
Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words Open
Shape-Text matching is an important task of high-level shape understanding. Current methods mainly represent a 3D shape as multiple 2D rendered views, which obviously can not be understood well due to the structural ambiguity caused by sel…
View article: Part2Word: Learning Joint Embedding of Point Clouds and Text by Matching Parts to Words.
Part2Word: Learning Joint Embedding of Point Clouds and Text by Matching Parts to Words. Open
It is important to learn joint embedding for 3D shapes and text in different shape understanding tasks, such as shape-text matching, retrieval, and shape captioning. Current multi-view based methods learn a mapping from multiple rendered v…
View article: Symptomatic remission in schizophrenia affects employment outcomes; Instrumental activity of daily living is a determinant for non-remitted patients
Symptomatic remission in schizophrenia affects employment outcomes; Instrumental activity of daily living is a determinant for non-remitted patients Open
Background: Remission criteria were proposed by Andreasen for classifying patients with schizophrenia according to the severity of psychopathology. Up to the present time, there have been no cohort studies exploring the association between…
View article: Directing DNNs Attention for Facial Attribution Classification using Gradient-weighted Class Activation Mapping
Directing DNNs Attention for Facial Attribution Classification using Gradient-weighted Class Activation Mapping Open
Deep neural networks (DNNs) have a high accuracy on image classification tasks. However, DNNs trained by such dataset with co-occurrence bias may rely on wrong features while making decisions for classification. It will greatly affect the …
View article: Directing DNNs Attention for Facial Attribution Classification using Gradient-weighted Class Activation Mapping.
Directing DNNs Attention for Facial Attribution Classification using Gradient-weighted Class Activation Mapping. Open
Deep neural networks (DNNs) have a high accuracy on image classification tasks. However, DNNs trained by such dataset with co-occurrence bias may rely on wrong features while making decisions for classification. It will greatly affect the …
View article: Trends in Prevalence of Psychiatric Comorbidities among Patients with Moderate to Severe Psoriasis
Trends in Prevalence of Psychiatric Comorbidities among Patients with Moderate to Severe Psoriasis Open
not available. Disclosures: Study sponsored by Janssen.Copyright 2018 SKIN
View article: Qualitative and Quantitative Analysis of the Major Constituents in WLJ Herbal Tea Using Multiple Chromatographic Techniques
Qualitative and Quantitative Analysis of the Major Constituents in WLJ Herbal Tea Using Multiple Chromatographic Techniques Open
Quality control of Chinese herbal tea remains a challenge due to our poor knowledge of their complex chemical profile. This study aims to investigate the chemical composition of one of the best-selling and famous brand of beverage in China…
View article: Full 3D reconstruction of transparent objects
Full 3D reconstruction of transparent objects Open
Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades. However, none of them can be directly applied to transparent objects. This paper presents a fully automatic approach for reconstructing…
View article: Full 3D Reconstruction of Transparent Objects
Full 3D Reconstruction of Transparent Objects Open
Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades. However, none of them can be directly applied to transparent objects. This paper presents a fully automatic approach for reconstructing…
View article: The Alpha-2A Adrenergic Receptor Gene -1291C/G Single Nucleotide Polymorphism is Associated with the Efficacy of Methylphenidate in Treating Taiwanese Children and Adolescents with Attention-Deficit Hyperactivity Disorder
The Alpha-2A Adrenergic Receptor Gene -1291C/G Single Nucleotide Polymorphism is Associated with the Efficacy of Methylphenidate in Treating Taiwanese Children and Adolescents with Attention-Deficit Hyperactivity Disorder Open
The ADRA2A gene -1291C/G SNP is associated with the efficacy of MPH for the treatment of ADHD in Taiwanese children and adolescents. The responsive subjects bearing homozygous -1291G allele are more likely to have a better response to MPH …