A hybrid visual state-space model with progressive depth modulation for single image dehazing
Single image dehazing at high resolution must propagate scene-wide haze statistics efficiently while exploiting depth-related geometry without destabilizing training. Convolutional networks restore local detail but lack large-scale consistency, Transformer-style global modeling is computationally expensive, and geometry-aware methods can degrade when unreliable depth is injected too aggressively. We propose SSMDehazeNet, a hybrid visual state-space model with progressive depth modulation. A state-space branch propagates global haze statistics with linear complexity while a parallel local branch reconstructs structure at full resolution; the two are coupled inside a Parallel Hybrid State-Space Module so that both paths remain available at the same feature layer. Geometry is introduced progressively: a zero-initialized Spatial Depth Modulator gives it negligible influence early in training and lets its contribution be learned from data, and the depth-consistency objective is modulated by the current reconstruction residual. On the RESIDE SOTS benchmark, SSMDehazeNet achieves 42.48 dB/0.9968 (indoor) and 36.18 dB/0.9931 (outdoor) with favorable no-reference quality, and at $$512 \times 512$$ resolution it runs in 80.62 ms on an RTX 4090, substantially faster than heavy Transformer-based dehazing. Zero-shot evaluation on O-HAZE and NH-HAZE, a branch-level analysis, and a controlled geometry-corruption study further characterize its generalization and its reliance on the learned geometry cue.
Authors
- Haili Zhao
- Zhiwen Xie
Institutions
- Changchun University of Science and Technology (CN)
Publication Details
- Journal
- Scientific Reports
- Published
- 2026-11-18
- DOI
- https://doi.org/10.1038/s41598-026-78372-x
- Primary Topic
- Image Enhancement Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Changchun University of Science and Technology