Physically Guided Visual Mass Estimation from a Single RGB Image
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913089930133504 |
|---|---|
| author | Lee, Sungjae Jeong, Junhan Hong, Yeonjoo Kim, Kwang In |
| author_facet | Lee, Sungjae Jeong, Junhan Hong, Yeonjoo Kim, Kwang In |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20303 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Physically Guided Visual Mass Estimation from a Single RGB Image Lee, Sungjae Jeong, Junhan Hong, Yeonjoo Kim, Kwang In Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Physically Guided Visual Mass Estimation from a Single RGB Image |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.20303 |