cs.CVNov 5, 2026

FreePath: Neural Mean Free Path for Image Dehazing

Authors: Rongrong Gao, Jingxuan Feng, Wenyu Xu

Organizations: Tsinghua University · Wuchang University of Technology · The Hong Kong Polytechnic University

Abstract

Single image dehazing requires recovering scene radiance from visual responses that are weakened and veiled by participating media. Existing methods either invert explicit scattering variables, which can be unstable under complex scenes, or learn direct restoration mappings, which often discard the physical organization of haze formation. We present FreePath, a neural mean free path framework for image dehazing. Instead of estimating atmospheric parameters, FreePath represents dehazing as feature space path state restoration, inspired by the expected distance a visual response can propagate before interacting with haze. Within a residual encoder and decoder, the Mean Free Path Residual Block learns path and collision fields to guide haze constrained correction, while FreePath State Conservation Integration preserves restored path states during deep feature aggregation. Experiments on paired CDD-11 haze images and real RTTS scenes show that FreePath consistently improves full reference fidelity, no reference perceptual quality, and visual faithfulness over representative dehazing baselines.

Figures & tables

Explore similar work

CardsList
  1. HNDiff: Haze-Noise Diffusion for Image Dehazing

    Aug 11, 2026Jin-Ting He, Fu-Jen Tsai, Yan-Tsung Peng +3Physics-Informed Diffusion ModelsDiffusion Models for Image Restoration

  2. RTE-FM-Dehazer: Radiative Transfer Equation Inspired Flow Matching for Real-World Image Dehazing

    Jul 2, 2026Chenfeng Wei, Chun Wang, Boyang Zhao +3Flow MatchingRadiative Transfer

  3. Hihaze: One-Step Diffusion for High-Resolution Real-World Image Dehazing

    Oct 19, 2026Zheng Chen, Yuchen Huang, Xiaoyang Liu +3Image DehazingDiffusion Models for Image Restoration