{"ID":2892447,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16034","arxiv_id":"2507.16034","title":"Privacy-Preserving Semantic Segmentation from Ultra-Low-Resolution RGB Inputs","abstract":"RGB-based semantic segmentation has become a mainstream approach for visual perception and is widely applied in a variety of downstream tasks. However, existing methods typically rely on high-resolution RGB inputs, which may expose sensitive visual content in privacy-critical environments. Ultra-low-resolution RGB sensing suppresses sensitive information directly during image acquisition, making it an attractive privacy-preserving alternative. Nevertheless, recovering semantic segmentation from ultra-low-resolution RGB inputs remains highly challenging due to severe visual degradation. In this work, we introduce a novel fully joint-learning framework to mitigate the optimization conflicts exacerbated by visual degradation for ultra-low-resolution semantic segmentation. Experiments demonstrate that our method outperforms representative baselines in semantic segmentation performance and our ultra-low-resolution RGB input achieves a favorable trade-off between privacy preservation and semantic segmentation performance. We deploy our privacy-preserving semantic segmentation method in a real-world robotic object-goal navigation task, demonstrating successful downstream task execution even under severe visual degradation.","short_abstract":"RGB-based semantic segmentation has become a mainstream approach for visual perception and is widely applied in a variety of downstream tasks. However, existing methods typically rely on high-resolution RGB inputs, which may expose sensitive visual content in privacy-critical environments. Ultra-low-resolution RGB sens...","url_abs":"https://arxiv.org/abs/2507.16034","url_pdf":"https://arxiv.org/pdf/2507.16034v2","authors":"[\"Xuying Huang\",\"Sicong Pan\",\"Olga Zatsarynna\",\"Juergen Gall\",\"Maren Bennewitz\"]","published":"2025-07-21T19:53:40Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\"]","methods":"[]","has_code":false}