---
title: "Physically Guided Visual Mass Estimation from a Single RGB Image"
authors:
  - "Sungjae Lee"
  - "Junhan Jeong"
  - "Yeonjoo Hong"
  - "Kwang In Kim"
doi: "10.24963/ijcai.2026/145"
url: "https://ijcai.org/proceedings/2026/145"
pdf: "https://ijcai.org/proceedings/2026/0145.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "1297-1305"
track: "Main Track"
keywords:
  - "Robotics: Perception"
  - "Computer Vision: Vision, language and reasoning"
  - "Computer Vision: Multimodal learning"
---

# Physically Guided Visual Mass Estimation from a Single RGB Image

Sungjae Lee, Junhan Jeong, Yeonjoo Hong, Kwang In Kim

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 1297-1305. DOI: [10.24963/ijcai.2026/145](https://doi.org/10.24963/ijcai.2026/145)

## 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.