Bi-modal Prediction and Transformation Coding for Compressing Complex Human Dynamics

ArXiv.org · 2025-09-21

For dynamic human motion sequences, the original KeyNode-Driven codec often struggles to retain compression efficiency when confronted with rapid movements or strong non-rigid deformations. This paper proposes a novel Bi-modal coding framework that enhances the flexibility of motion representation by integrating semantic segmentation and region-specific transformation modeling. The rigid transformation model (rotation & translation) is extended with a hybrid scheme that selectively applies affine transformations-rotation, translation, scaling, and shearing-only to deformation-rich regions (e.g., the torso, where loose clothing induces high variability), while retaining rigid models elsewhere. The affine model is decomposed into minimal parameter sets for efficient coding and combined through a component selection strategy guided by a Lagrangian Rate-Distortion optimization. The results show that the Bi-modal method achieves more accurate mesh deformation, especially in sequences involving complex non-rigid motion, without compromising compression efficiency in simpler regions, with an average bit-rate saving of 33.81% compared to the baseline.

THP3D: Text-Driven Multi-granularity 3D Human Parsing

Lecture notes in computer science · 2025-01-01 · 1 citations

Image-Conditioned 3D Gaussian Splat Quantization

ArXiv.org · 2025-08-21

3D Gaussian Splatting (3DGS) has attracted considerable attention for enabling high-quality real-time rendering. Although 3DGS compression methods have been proposed for deployment on storage-constrained devices, two limitations hinder archival use: (1) they compress medium-scale scenes only to the megabyte range, which remains impractical for large-scale scenes or extensive scene collections; and (2) they lack mechanisms to accommodate scene changes after long-term archival. To address these limitations, we propose an Image-Conditioned Gaussian Splat Quantizer (ICGS-Quantizer) that substantially enhances compression efficiency and provides adaptability to scene changes after archiving. ICGS-Quantizer improves quantization efficiency by jointly exploiting inter-Gaussian and inter-attribute correlations and by using shared codebooks across all training scenes, which are then fixed and applied to previously unseen test scenes, eliminating the overhead of per-scene codebooks. This approach effectively reduces the storage requirements for 3DGS to the kilobyte range while preserving visual fidelity. To enable adaptability to post-archival scene changes, ICGS-Quantizer conditions scene decoding on images captured at decoding time. The encoding, quantization, and decoding processes are trained jointly, ensuring that the codes, which are quantized representations of the scene, are effective for conditional decoding. We evaluate ICGS-Quantizer on 3D scene compression and 3D scene updating. Experimental results show that ICGS-Quantizer consistently outperforms state-of-the-art methods in compression efficiency and adaptability to scene changes. Our code, model, and data will be publicly available on GitHub.

A Single Centre Case Series of Posteroseptal Accessory Pathway Ablation via the Percutaneous Epicardial Approach Following Failed Endocardial Ablation

Heart Lung and Circulation · 2025-08-01

Pointwise Structure–Function Analysis of the Ellipsoid Zone in Retinitis Pigmentosa Using an Artificial Intelligence-Assisted OCT and Microperimetry Overlay

Ophthalmology Science · 2025-07-22

Objective: To perform a pointwise structure-function analysis of the ellipsoid zone (EZ) in retinitis pigmentosa (RP) using an artificial intelligence-based overlay to understand EZ structure-function relationships. Design: A single-center retrospective study. Subjects: Patients with clinically confirmed RP. Methods: Same-day spectral-domain OCT (SD-OCT) and microperimetry near-infrared images were overlaid in patients with confirmed RP. Overlay used a coarse alignment artificial intelligence model. Each locus, on a 68-point microperimetry grid spanning the central 20° of the macula, was identified on individual SD-OCT B-scans. Ellipsoid zone structure was graded at each locus on a 3-point scale: grade 0 = EZ not visible; grade 1 = EZ attenuated; grade 2 = EZ normal. Ellipsoid zone grades were correlated with microperimetry sensitivity scores recorded in decibels (dB). Main Outcome Measures: Correlation of EZ integrity on SD-OCT with microperimetric retinal sensitivity. Results: < 0.001). Correlation between EZ grade and sensitivity was 0.65 (0.64-0.67), whereas correlation of sensitivity with distance from the fovea was -0.41 (-0.43 to -0.39). Focusing on grade 0 loci, 57.5% had sensitivity scores >0 dB, and 4% had scores ≥20 dB, suggesting that these points had function despite no observable EZ on SD-OCT. Conclusions: We identified local EZ structure-function incongruencies in RP using a pointwise analysis of structure-function overlay. These loci of interest may be overlooked in analyses that average across the visual field. Preserved photoreceptor function, in the absence of visibly intact EZ, warrants further investigation. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Universal Vessel Segmentation for Multi-Modality Retinal Images

IEEE Transactions on Image Processing · 2025-01-01

We identify two major limitations in the existing studies on retinal vessel segmentation: 1) Most existing works are restricted to one modality, i.e., the Color Fundus (CF). However, multi-modality retinal images are used every day in the study of the retina and diagnosis of retinal diseases, and the study of vessel segmentation on other modalities is scarce; 2) Even though a few works extended their experiments to new modalities such as the Multi-Color Scanning Laser Ophthalmoscopy (MC), these works still require fine-tuning a separate model for the new modality. The fine-tuning will require extra training data, which is difficult to acquire. In this work, we present a novel universal vessel segmentation model (URVSM) for multi-modality retinal images. In addition to performing the study on a much wider range of image modalities, we also propose a universal model to segment the vessels in all these commonly used modalities. While being much more versatile compared with existing methods, our universal model also demonstrates comparable performance to the state-of-the-art fine-tuned methods. To the best of our knowledge, this is the first work that achieves modality-agnostic retinal vessel segmentation and the first to study retinal vessel segmentation in several novel modalities (Code, model and 3 new retinal vessel segmentation datasets are available at https://github.com/JRC-VPLab/URVSM).

Enhancing Healthcare Data Integration: A Machine Learning Approach to Harmonizing Laboratory Labels.

PubMed · 2025-01-01

Variations in laboratory test names across healthcare systems-stemming from inconsistent terminologies, abbreviations, misspellings, and assay vendors-pose significant challenges to the integration and analysis of clinical data. These discrepancies hinder interoperability and complicate efforts to extract meaningful insights for both clinical research and patient care. In this study, we propose a machine learning-driven solution, enhanced by natural language processing techniques, to standardize lab test names. By employing feature extraction methods that analyze both string similarity and the distributional properties of test results, we improve the harmonization of test names, resulting in a more robust dataset. Our model achieves a 99% accuracy rate in matching lab names, showcasing the potential of AI-driven approaches in resolving long-standing standardization challenges. Importantly, this method enhances the reliability and consistency of clinical data, which is crucial for ensuring accurate results in large-scale clinical studies and improving the overall efficiency of informatics-based research and diagnostics.

Universal Vessel Segmentation for Multi-Modality Retinal Images

arXiv (Cornell University) · 2025-02-10

We identify two major limitations in the existing studies on retinal vessel segmentation: (1) Most existing works are restricted to one modality, i.e., the Color Fundus (CF). However, multi-modality retinal images are used every day in the study of the retina and diagnosis of retinal diseases, and the study of vessel segmentation on other modalities is scarce; (2) Even though a few works extended their experiments to new modalities such as the Multi-Color Scanning Laser Ophthalmoscopy (MC), these works still require fine-tuning a separate model for the new modality. The fine-tuning will require extra training data, which is difficult to acquire. In this work, we present a novel universal vessel segmentation model (URVSM) for multi-modality retinal images. In addition to performing the study on a much wider range of image modalities, we also propose a universal model to segment the vessels in all these commonly used modalities. While being much more versatile compared with existing methods, our universal model also demonstrates comparable performance to the state-of-the-art fine-tuned methods. To the best of our knowledge, this is the first work that achieves modality-agnostic retinal vessel segmentation and the first to study retinal vessel segmentation in several novel modalities.

Universal Wavelet Units in 3D Retinal Layer Segmentation

ArXiv.org · 2025-07-22

This paper presents the first study to apply tunable wavelet units (UwUs) for 3D retinal layer segmentation from Optical Coherence Tomography (OCT) volumes. To overcome the limitations of conventional max-pooling, we integrate three wavelet-based downsampling modules, OrthLattUwU, BiorthLattUwU, and LS-BiorthLattUwU, into a motion-corrected MGU-Net architecture. These modules use learnable lattice filter banks to preserve both low- and high-frequency features, enhancing spatial detail and structural consistency. Evaluated on the Jacobs Retina Center (JRC) OCT dataset, our framework shows significant improvement in accuracy and Dice score, particularly with LS-BiorthLattUwU, highlighting the benefits of tunable wavelet filters in volumetric medical image segmentation.

Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems

ArXiv.org · 2025-07-21

This work introduces a stop-band energy constraint for filters in orthogonal tunable wavelet units with a lattice structure, aimed at improving image classification and anomaly detection in CNNs, especially on texture-rich datasets. Integrated into ResNet-18, the method enhances convolution, pooling, and downsampling operations, yielding accuracy gains of 2.48% on CIFAR-10 and 13.56% on the Describable Textures dataset. Similar improvements are observed in ResNet-34. On the MVTec hazelnut anomaly detection task, the proposed method achieves competitive results in both segmentation and detection, outperforming existing approaches.