arXiv subjects

Itaru Kitahara

Publications and source records attributed to Itaru Kitahara.

10 recordsLinked to original sources

arXiv2026

MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation

Implicit SDF-based methods for single-view 3D reconstruction achieve high-quality surfaces but require large labeled datasets, limiting their scalability. We propose MetaSSP, a novel semi-supervised framework that exploits abundant unlabeled images. Our approach introduces gradient-based parameter importance estimation to regularize adaptive EMA updates and an SDF-aware pseudo-label weighting mechanism combining augmentation consistency with SDF variance. Beginning with a 10% supervised warm-up, the unified pipeline jointly refines labeled and unlabeled data. On the Pix3D benchmark, our method reduces Chamfer Distance by approximately 20.61% and increases IoU by around 24.09% compared to existing semi-supervised baselines, setting a new state of the art.

cs.CV↗

arXiv2026

MGP-KAD: Multimodal Geometric Priors and Kolmogorov-Arnold Decoder for Single-View 3D Reconstruction in Complex Scenes

Single-view 3D reconstruction in complex real-world scenes is challenging due to noise, object diversity, and limited dataset availability. To address these challenges, we propose MGP-KAD, a novel multimodal feature fusion framework that integrates RGB and geometric prior to enhance reconstruction accuracy. The geometric prior is generated by sampling and clustering ground-truth object data, producing class-level features that dynamically adjust during training to improve geometric understanding. Additionally, we introduce a hybrid decoder based on Kolmogorov-Arnold Networks (KAN) to overcome the limitations of traditional linear decoders in processing complex multimodal inputs. Extensive experiments on the Pix3D dataset demonstrate that MGP-KAD achieves state-of-the-art (SOTA) performance, significantly improving geometric integrity, smoothness, and detail preservation. Our work provides a robust and effective solution for advancing single-view 3D reconstruction in complex scenes.

cs.CV↗

arXiv2025

SV-DRR: High-Fidelity Novel View X-Ray Synthesis Using Diffusion Model

X-ray imaging is a rapid and cost-effective tool for visualizing internal human anatomy. While multi-view X-ray imaging provides complementary information that enhances diagnosis, intervention, and education, acquiring images from multiple angles increases radiation exposure and complicates clinical workflows. To address these challenges, we propose a novel view-conditioned diffusion model for synthesizing multi-view X-ray images from a single view. Unlike prior methods, which are limited in angular range, resolution, and image quality, our approach leverages the Diffusion Transformer to preserve fine details and employs a weak-to-strong training strategy for stable high-resolution image generation. Experimental results demonstrate that our method generates higher-resolution outputs with improved control over viewing angles. This capability has significant implications not only for clinical applications but also for medical education and data extension, enabling the creation of diverse, high-quality datasets for training and analysis. Our code is available at https://github.com/xiechun298/SV-DRR.

eess.IV↗

arXiv2025

Measurement of Medial Elbow Joint Space using Landmark Detection

Ultrasound imaging of the medial elbow is crucial for the early diagnosis of Ulnar Collateral Ligament (UCL) injuries. Specifically, measuring the elbow joint space in ultrasound images is used to assess the valgus instability of the elbow caused by UCL injuries. To automate this measurement, a model trained on a precisely annotated dataset is necessary; however, no publicly available dataset exists to date. This study introduces a novel ultrasound medial elbow dataset to measure the joint space. The dataset comprises 4,201 medial elbow ultrasound images from 22 subjects, with landmark annotations on the humerus and ulna, based on the expertise of three orthopedic surgeons. We evaluated joint space measurement methods on our proposed dataset using heatmap-based, regression-based, and token-based landmark detection methods. While heatmap-based landmark detection methods generally achieve high accuracy, they sometimes produce multiple peaks on a heatmap, leading to incorrect detection. To mitigate this issue and enhance landmark localization, we propose Shape Subspace (SS) landmark refinement by measuring geometrical similarities between the detected and reference landmark positions. The results show that the mean joint space measurement error is 0.116 mm when using HRNet. Furthermore, SS landmark refinement can reduce the mean absolute error of landmark positions by 0.010 mm with HRNet and by 0.103 mm with ViTPose on average. These highlight the potential for high-precision, real-time diagnosis of UCL injuries by accurately measuring joint space. Lastly, we demonstrate point-based segmentation for the humerus and ulna using the detected landmarks as inputs. Our dataset will be publicly available at https://github.com/Akahori000/Ultrasound-Medial-Elbow-Dataset

cs.CV↗

arXiv2025

Detection of Medial Epicondyle Avulsion in Elbow Ultrasound Images via Bone Structure Reconstruction

This study proposes a reconstruction-based framework for detecting medial epicondyle avulsion in elbow ultrasound images, trained exclusively on normal cases. Medial epicondyle avulsion, commonly observed in baseball players, involves bone detachment and deformity, often appearing as discontinuities in bone contour. Therefore, learning the structure and continuity of normal bone is essential for detecting such abnormalities. To achieve this, we propose a masked autoencoder-based, structure-aware reconstruction framework that learns the continuity of normal bone structures. Even in the presence of avulsion, the model attempts to reconstruct the normal structure, resulting in large reconstruction errors at the avulsion site. For evaluation, we constructed a novel dataset comprising normal and avulsion ultrasound images from 16 baseball players, with pixel-level annotations under orthopedic supervision. Our method outperformed existing approaches, achieving a pixel-wise AUC of 0.965 and an image-wise AUC of 0.967. The dataset is publicly available at: https://github.com/Akahori000/Ultrasound-Medial-Epicondyle-Avulsion-Dataset.

cs.CV↗

arXiv2024

M3D: Dual-Stream Selective State Spaces and Depth-Driven Framework for High-Fidelity Single-View 3D Reconstruction

The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant difficulties in balancing the extraction of global and local features, particularly in diverse and complex environments, leading to insufficient reconstruction precision and quality. We propose M3D, a novel single-view 3D reconstruction framework, to tackle these challenges. This framework adopts a dual-stream feature extraction strategy based on Selective State Spaces to effectively balance the extraction of global and local features, thereby improving scene comprehension and representation precision. Additionally, a parallel branch extracts depth information, effectively integrating visual and geometric features to enhance reconstruction quality and preserve intricate details. Experimental results indicate that the fusion of multi-scale features with depth information via the dual-branch feature extraction significantly boosts geometric consistency and fidelity, achieving state-of-the-art reconstruction performance.

cs.CV↗

arXiv2024

RayEmb: Arbitrary Landmark Detection in X-Ray Images Using Ray Embedding Subspace

Intra-operative 2D-3D registration of X-ray images with pre-operatively acquired CT scans is a crucial procedure in orthopedic surgeries. Anatomical landmarks pre-annotated in the CT volume can be detected in X-ray images to establish 2D-3D correspondences, which are then utilized for registration. However, registration often fails in certain view angles due to poor landmark visibility. We propose a novel method to address this issue by detecting arbitrary landmark points in X-ray images. Our approach represents 3D points as distinct subspaces, formed by feature vectors (referred to as ray embeddings) corresponding to intersecting rays. Establishing 2D-3D correspondences then becomes a task of finding ray embeddings that are close to a given subspace, essentially performing an intersection test. Unlike conventional methods for landmark estimation, our approach eliminates the need for manually annotating fixed landmarks. We trained our model using the synthetic images generated from CTPelvic1K CLINIC dataset, which contains 103 CT volumes, and evaluated it on the DeepFluoro dataset, comprising real X-ray images. Experimental results demonstrate the superiority of our method over conventional methods. The code is available at https://github.com/Pragyanstha/rayemb.

cs.CV↗

arXiv2022

Size Does Matter: An Experimental Study of Anxiety in Virtual Reality

The emotional response of users induced by VR scenarios has become a topic of interest, however, whether changing the size of objects in VR scenes induces different levels of anxiety remains a question to be studied. In this study, we conducted an experiment to initially reveal how the size of a large object in a VR environment affects changes in participants' (N = 38) anxiety level and heart rate. To holistically quantify the size of large objects in the VR visual field, we used the omnidirectional field of view occupancy (OFVO) criterion for the first time to represent the dimension of the object in the participant's entire field of view. The results showed that the participants' heartbeat and anxiety while viewing the large objects were positively and significantly correlated to OFVO. These study reveals that the increase of object size in VR environments is accompanied by a higher degree of user's anxiety.

cs.MM↗

arXiv2022

OmniVoxel: A Fast and Precise Reconstruction Method of Omnidirectional Neural Radiance Field

This paper proposes a method to reconstruct the neural radiance field with equirectangular omnidirectional images. Implicit neural scene representation with a radiance field can reconstruct the 3D shape of a scene continuously within a limited spatial area. However, training a fully implicit representation on commercial PC hardware requires a lot of time and computing resources (15 $\sim$ 20 hours per scene). Therefore, we propose a method to accelerate this process significantly (20 $\sim$ 40 minutes per scene). Instead of using a fully implicit representation of rays for radiance field reconstruction, we adopt feature voxels that contain density and color features in tensors. Considering omnidirectional equirectangular input and the camera layout, we use spherical voxelization for representation instead of cubic representation. Our voxelization method could balance the reconstruction quality of the inner scene and outer scene. In addition, we adopt the axis-aligned positional encoding method on the color features to increase the total image quality. Our method achieves satisfying empirical performance on synthetic datasets with random camera poses. Moreover, we test our method with real scenes which contain complex geometries and also achieve state-of-the-art performance. Our code and complete dataset will be released at the same time as the paper publication.

cs.CV↗

arXiv2022

Neural Density-Distance Fields

The success of neural fields for 3D vision tasks is now indisputable. Following this trend, several methods aiming for visual localization (e.g., SLAM) have been proposed to estimate distance or density fields using neural fields. However, it is difficult to achieve high localization performance by only density fields-based methods such as Neural Radiance Field (NeRF) since they do not provide density gradient in most empty regions. On the other hand, distance field-based methods such as Neural Implicit Surface (NeuS) have limitations in objects' surface shapes. This paper proposes Neural Density-Distance Field (NeDDF), a novel 3D representation that reciprocally constrains the distance and density fields. We extend distance field formulation to shapes with no explicit boundary surface, such as fur or smoke, which enable explicit conversion from distance field to density field. Consistent distance and density fields realized by explicit conversion enable both robustness to initial values and high-quality registration. Furthermore, the consistency between fields allows fast convergence from sparse point clouds. Experiments show that NeDDF can achieve high localization performance while providing comparable results to NeRF on novel view synthesis. The code is available at https://github.com/ueda0319/neddf.

cs.CV↗