{"ID":2863660,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.24863","arxiv_id":"2509.24863","title":"Vision At Night: Exploring Biologically Inspired Preprocessing For Improved Robustness Via Color And Contrast Transformations","abstract":"Inspired by the human visual system's mechanisms for contrast enhancement and color-opponency, we explore biologically motivated input preprocessing for robust semantic segmentation. By applying Difference-of-Gaussians (DoG) filtering to RGB, grayscale, and opponent-color channels, we enhance local contrast without modifying model architecture or training. Evaluations on Cityscapes, ACDC, and Dark Zurich show that such preprocessing maintains in-distribution performance while improving robustness to adverse conditions like night, fog, and snow. As this processing is model-agnostic and lightweight, it holds potential for integration into imaging pipelines, enabling imaging systems to deliver task-ready, robust inputs for downstream vision models in safety-critical environments.","short_abstract":"Inspired by the human visual system's mechanisms for contrast enhancement and color-opponency, we explore biologically motivated input preprocessing for robust semantic segmentation. By applying Difference-of-Gaussians (DoG) filtering to RGB, grayscale, and opponent-color channels, we enhance local contrast without mod...","url_abs":"https://arxiv.org/abs/2509.24863","url_pdf":"https://arxiv.org/pdf/2509.24863v1","authors":"[\"Lorena Stracke\",\"Lia Nimmermann\",\"Shashank Agnihotri\",\"Margret Keuper\",\"Volker Blanz\"]","published":"2025-09-29T14:48:32Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}