VolTex: Food Volume Estimation using Text-Guided Segmentation and Neural Surface Reconstruction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910983340949504 |
|---|---|
| author | AlMughrabi, Ahmad Haroon, Umair Marques, Ricardo Radeva, Petia |
| author_facet | AlMughrabi, Ahmad Haroon, Umair Marques, Ricardo Radeva, Petia |
| contents | Accurate food volume estimation is crucial for dietary monitoring, medical nutrition management, and food intake analysis. Existing 3D Food Volume estimation methods accurately compute the food volume but lack for food portions selection. We present VolTex, a framework that improves \change{the food object selection} in food volume estimation. Allowing users to specify a target food item via text input to be segmented, our method enables the precise selection of specific food objects in real-world scenes. The segmented object is then reconstructed using the Neural Surface Reconstruction method to generate high-fidelity 3D meshes for volume computation. Extensive evaluations on the MetaFood3D dataset demonstrate the effectiveness of our approach in isolating and reconstructing food items for accurate volume estimation. The source code is accessible at https://github.com/GCVCG/VolTex. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02895 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VolTex: Food Volume Estimation using Text-Guided Segmentation and Neural Surface Reconstruction AlMughrabi, Ahmad Haroon, Umair Marques, Ricardo Radeva, Petia Graphics Computer Vision and Pattern Recognition Accurate food volume estimation is crucial for dietary monitoring, medical nutrition management, and food intake analysis. Existing 3D Food Volume estimation methods accurately compute the food volume but lack for food portions selection. We present VolTex, a framework that improves \change{the food object selection} in food volume estimation. Allowing users to specify a target food item via text input to be segmented, our method enables the precise selection of specific food objects in real-world scenes. The segmented object is then reconstructed using the Neural Surface Reconstruction method to generate high-fidelity 3D meshes for volume computation. Extensive evaluations on the MetaFood3D dataset demonstrate the effectiveness of our approach in isolating and reconstructing food items for accurate volume estimation. The source code is accessible at https://github.com/GCVCG/VolTex. |
| title | VolTex: Food Volume Estimation using Text-Guided Segmentation and Neural Surface Reconstruction |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.02895 |