Experiments on HDRTV1K show that Bio-SFT achieves competitive perceptual quality and consistently improves HDR-VDP-3 and $\Delta E_{ITP}$ while reducing artifact propagation in symmetric guidance pipelines.
Abstract
Recovering high dynamic range (HDR) radiance from a single standard dynamic range (SDR) image is highly ill-posed. Extreme luminance variation and severe quantization in dark regions make accurate reconstruction challenging, often leading to visual artifacts and color distortions. To address this problem, we propose Bio-SFT, a bio-inspired spiking frequency transformer for single-image HDR reconstruction. Bio-SFT incorporates three biologically motivated components. First, a learnable Naka--Rushton retinal adaptation frontend stabilizes the input under complex lighting conditions. Second, an explicit Parvo--Magno split introduces asymmetric Parvo-to-Magno guidance, allowing high-frequency structural cues to modulate low-frequency reconstruction. Third, an event-driven SNN hard gating module applies all-or-none spiking to suppress dark-region noise while preserving structural details. The module is trained with a sparsity prior to encourage efficient feature utilization. Built for end-to-end training within a transformer backbone, these lightweight components provide strong parameter efficiency. Experiments on HDRTV1K show that Bio-SFT achieves competitive perceptual quality and consistently improves HDR-VDP-3 and $\Delta E_{ITP}$ while reducing artifact propagation in symmetric guidance pipelines.
This work pioneers the synergistic integration of SNNs into Transformer architectures for LLIE, establishing a compelling pathway toward powerful, energy-efficient low-level vision on resource-constrained platforms.
Hongzhi Wang, Xiubo Liang, Jinxing Han et al.· Advances in Neural Informati...· 0 citations
This work proposes Structure-Anchored Rectified Flow (SA-RF), which maintains correspondence through separate chromaticity/intensity stems, a scale-matched condition pyramid, and HybridAda, and introduces BC-IHV, a learnable Box--Cox polar color space whose analytically invertible intensity mapping controls the inverse-gradient dynamic range through a single exponent.
Yihao Ai, Zheng Chen, Yuanhao Cai et al.· 0 citations
DCRM-ViT is proposed, a domain-conditioned residual modulation framework for Vision Transformers that preserves general-vision knowledge while adapting to diverse medical and natural domains and achieves strong cross-domain performance with low overhead.
Ufaq Khan, Umair Nawaz, Massimo Caputo et al.· 0 citations
Automated Accurate segmentation of retinal layers from optical coherence tomography (OCT) volumes is a prerequisite for the quantitative assessment of neurodegenerative and macular diseases. Yet the task is complicated by low interlayer contrast, imaging noise, and wide anatomical variability across patients. In this work we introduce OmniSEG, an ensemble framework that combines a nested UNet with dense skip connections (UNet++), a Swin Transformer-based UNet (SwinUNet), and an attention-guided surface auto-encoder into a unified training pipeline. The model is trained on the publicly available GOALS-2022 dataset using a compound loss that mixes focal cross-entropy, Tversky, gradient-based boundary, and surface smoothness terms while remaining numerically stable under automatic mixed precision (AMP). After 200 epochs the ensemble reaches a mean Dice of 0.864 across six foreground retinal classes, with a surface RMSE decreasing from 122 pixels to 76.5 pixels. Per-class analysis reveals that the OPL class benefits earliest from training (Dice > 0.10 at epoch 197), which reflects early-stage learning on a relatively wider layer rather than a final result, consistent with its wider span and higher contrast relative to thinner layers such as RNFL. These results establish a reproducible baseline for multi-class OCT segmentation and identify concrete directions for future improvement.
Assma Ihiya, Fouad Yakoubi, Bahia Ouazzani Chahdi et al.· IEEE International Conferenc...· 0 citations
DSF-Net provides a robust framework for improving vessel continuity and boundary delineation in fundus images and produces more accurate and structurally coherent segmentation results, especially for thin and complex vessels.
Feng Liang, Xiaoqi Sheng, Yang Liu et al.· Frontiers of Computer Scienc...· 0 citations
Comprehensive evaluations on multiple datasets and SR scales indicate that the SVRCL-SR achieves superior performance in artifact suppression and high-frequency detail restoration, along with strong robustness.
Qian Tong, Chaoliang He, Chuandong Tan et al.· Measurement science and tech...· 0 citations
