{"type":"ScholarlyArticle","title":"MLLM-ITM: Multimodal Large Language Model Promotes Inverse Tone Mapping","authors":[{"name":"Jingchao Peng","slug":"jingchao-peng","given":"Jingchao","family":"Peng","affiliation":""},{"name":"Thomas Bashford-Rogers","slug":"thomas-bashford-rogers","given":"Thomas","family":"Bashford-Rogers","affiliation":""},{"name":"Haitao Zhao","slug":"haitao-zhao","given":"Haitao","family":"Zhao","affiliation":""},{"name":"Kurt Debattista","slug":"kurt-debattista","given":"Kurt","family":"Debattista","affiliation":""}],"abstract":"High dynamic range (HDR) imaging is crucial for capturing real-world lighting conditions.\r\nHDR imaging is traditionally achieved either by fusing multiple exposure frames or via inverse tone mapping from a single SDR image.\r\nHowever, the multi-exposure HDR method is prone to motion-induced artefacts and imposes demanding hardware requirements, limiting its practical applicability. \r\nTraditional inverse tone-mapping techniques primarily rely on pixel-wise regression methods, which ignore semantic scene contexts and thus frequently introduce halo artefacts and structural distortions.\r\nTo address this limitation, this paper proposes MLLM-ITM, a novel inverse tone-mapping framework incorporating multimodal large language models (MLLMs). \r\nMLLM-ITM utilizes cross-modal features extracted from a frozen MLLM to simultaneously encode visual features and semantic understanding. These features are integrated into a downstream HDR reconstruction backbone through lightweight adapters, enabling content-aware dynamic-range expansion.\r\nFurthermore, the decoupled design between MLLM and HDR backbone avoids costly fine-tuning of MLLMs and remains model-agnostic, allowing effortless substitution with emerging multimodal architectures. Extensive experiments on public benchmarks demonstrate that the proposed MLLM-ITM achieves state-of-the-art performance compared with existing inverse tone-mapping methods, highlighting the effectiveness of cross-modal semantic priors in enhancing HDR imaging performance.","doi":"10.24963/ijcai.2026/169","url":"https://ijcai.org/proceedings/2026/169","pdf":"https://ijcai.org/proceedings/2026/0169.pdf","markdown":"https://ijcai.org/proceedings/2026/169.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/169","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":169,"pages":{"first":1514,"last":1522},"keywords":["Computer Vision: Machine learning for vision","Computer Vision: Image and video synthesis and generation","Computer Vision: Multimodal learning","Computer Vision: Low-level Vision"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}