{"type":"ScholarlyArticle","title":"SPACE: Structure-Preserving Cross-Modal Image Enhancement for Extreme Low-Light Conditions","authors":[{"name":"Yue Zhang","slug":"yue-zhang","given":"Yue","family":"Zhang","affiliation":""},{"name":"Zhiliang Wu","slug":"zhiliang-wu","given":"Zhiliang","family":"Wu","affiliation":""},{"name":"Yuxuan Hou","slug":"yuxuan-hou","given":"Yuxuan","family":"Hou","affiliation":""},{"name":"Hehe Fan","slug":"hehe-fan","given":"Hehe","family":"Fan","affiliation":""}],"abstract":"Low-Light Image Enhancement (LLIE) remains challenging due to severe noise, color artifacts, and structural degradation in extreme low-light environments. Existing methods primarily rely on photometric cues and often fail to preserve geometric consistency, resulting in blurred edges and distorted textures. To address this limitation, we introduce LAMP, a large-scale dataset of Low-light Aligned Multimodal Pairs for LLIE. LAMP contains over 18k high-quality aligned pairs and consists of two complementary subsets. LAMP-Real is captured using LiDAR-based depth sensors under physically controlled illumination, while LAMP-Synthetic is generated through a physics-calibrated degradation pipeline. Both subsets provide precisely aligned RGB images, depth maps, and pixel-wise semantic annotations. Building upon LAMP, we propose SPACE, a Structure Preservation Aware Cross-modal Enhancement framework that explicitly leverages geometric priors. SPACE introduces a Depth-Adaptive HVI Transformation to decouple luminance and chrominance under depth guidance, effectively suppressing color-space noise. Furthermore, a Depth-Manifold Modulated Attention mechanism constrains feature interactions within a learned depth manifold, ensuring structural coherence during enhancement. Extensive experiments demonstrate that SPACE consistently outperforms state-of-the-art methods in visual quality and structural fidelity. The code and data are available at https://github.com/YueCheong/SPACE.","doi":"10.24963/ijcai.2026/235","url":"https://ijcai.org/proceedings/2026/235","pdf":"https://ijcai.org/proceedings/2026/0235.pdf","markdown":"https://ijcai.org/proceedings/2026/235.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/235","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":235,"pages":{"first":2109,"last":2117},"keywords":["Computer Vision: Low-level Vision","Computer Vision: Multimodal learning","AI: Computer Vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}