{"type":"ScholarlyArticle","title":"Physically Guided Visual Mass Estimation from a Single RGB Image","authors":[{"name":"Sungjae Lee","slug":"sungjae-lee","given":"Sungjae","family":"Lee","affiliation":""},{"name":"Junhan Jeong","slug":"junhan-jeong","given":"Junhan","family":"Jeong","affiliation":""},{"name":"Yeonjoo Hong","slug":"yeonjoo-hong","given":"Yeonjoo","family":"Hong","affiliation":""},{"name":"Kwang In Kim","slug":"kwang-in-kim","given":"Kwang In","family":"Kim","affiliation":""}],"abstract":"Estimating object mass from visual input is challenging because mass depends jointly on geometric volume and material-dependent density, neither of which is directly observable from RGB appearance. Consequently, mass prediction from pixels is ill-posed and therefore benefits from physically meaningful representations to constrain the space of plausible solutions. We propose a physically structured framework for single-image mass estimation that addresses this ambiguity by aligning visual cues with the physical factors governing mass. From a single RGB image, we recover object-centric three-dimensional geometry via monocular depth estimation to inform volume and extract coarse material semantics using a vision-language model to guide density-related reasoning. These geometry, semantic, and appearance representations are fused through an instance-adaptive gating mechanism, and two physically guided latent factors (volume- and density-related) are predicted through separate regression heads under mass-only supervision. Experiments on image2mass and ABO-500 show that the proposed method consistently outperforms state-of-the-art methods.","doi":"10.24963/ijcai.2026/145","url":"https://ijcai.org/proceedings/2026/145","pdf":"https://ijcai.org/proceedings/2026/0145.pdf","markdown":"https://ijcai.org/proceedings/2026/145.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/145","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":145,"pages":{"first":1297,"last":1305},"keywords":["Robotics: Perception","Computer Vision: Vision, language and reasoning","Computer Vision: Multimodal learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}