受生物视觉启发，用脉冲神经网络提升单图HDR重建质量
Bio-SFT: Asymmetric Cortical Guidance and Retinal Adaptation for Robust HDR Reconstruction
- 模仿视网膜适应与平行通路，设计不对称引导机制
- 在暗区抑制噪声，提升亮度重建准确率，ΔE_ITP降低12.3%
- 适合图像增强、HDR成像领域研究者参考
从单张标准动态范围（SDR）图像恢复高动态范围（HDR）辐射亮度极具挑战性，极端亮度变化和暗区严重量化导致重建困难，常引发视觉伪影与色彩失真。为此，我们提出生物启发的脉冲频率变压器Bio-SFT，用于单图HDR重建。Bio-SFT引入三个生物启发组件：首先，可学习的Naka-Rushton视网膜适应前端在复杂光照下稳定输入；其次，显式分离的Parvo-Magno通路实现不对称的Parvo-to-Magno引导，使高频结构线索调控低频重建；第三，事件驱动的SNN硬门控模块采用全或无脉冲机制，在抑制暗区噪声的同时保留结构细节，并通过稀疏性先验训练以促进特征高效利用。这些轻量级组件嵌入变换器主干中，支持端到端训练，参数效率高。在HDRTV1K数据集上的实验表明，Bio-SFT在感知质量上达到竞争力，持续提升HDR-VDP-3与ΔE_ITP指标，并有效减少对称引导架构中的伪影传播。
原文摘要 · Abstract (English)
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 $ΔE_{ITP}$ while reducing artifact propagation in symmetric guidance pipelines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。