Pasar al contenido principal

HACER QUE EL APRENDIZAJE PROFUNDO FUNCIONE EN EL MUNDO REAL: UNA PERSPECTIVA CENTRADA EN LOS DATOS

PID2022-141566NB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE BARCELONA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Bayesian DivideMix++ for enhanced learning with noisy labels

  • Nagarajan, Bhalaji
  • Marques, Ricardo
  • Aguilar, Eduardo J.
  • Radeva, Petia
Leveraging inexpensive and human intervention-based annotating methodologies, such as crowdsourcing and web crawling, often leads to datasets with noisy labels. Noisy labels can have a detrimental impact on the performance and generalization of deep neural networks. Robust models that are able to handle and mitigate the effect of these noisy labels are thus essential. In this work, we explore the open challenges of neural network memorization and uncertainty in creating robust learning algorithms with noisy labels. To overcome them, we propose a novel framework called “Bayesian DivideMix++” with two critical components: (i) DivideMix++, to enhance the robustness against memorization and (ii) Monte-Carlo MixMatch, which focuses on improving the effectiveness towards label uncertainty. DivideMix++ improves the pipeline by integrating the warm-up and augmentation pipeline with self-supervised pre-training and dedicated different data augmentations for loss analysis and backpropagation. Monte-Carlo MixMatch leverages uncertainty measurements to mitigate the influence of uncertain samples by reducing their weight in the data augmentation MixMatch step. We validate our proposed pipeline using four datasets encompassing various synthetic and real-world noise settings. We demonstrate the effectiveness and merits of our proposed pipeline using extensive experiments. Bayesian DivideMix++ outperforms the state-of-the-art models by considerable differences in all experiments. Our findings underscore the potential of leveraging these modifications to enhance the performance and generalization of deep neural networks in practical scenarios., This work was partially funded by the Horizon EU project MUSAE (No. 01070421), 2021-SGR-01094 (AGAUR), Icrea Academia’2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220-VET-000089434, Erasmus+ EU), DeepSense (ACE053/22/000029, ACCIÓ), DeepFoodVol (AEI-MICINN, PDC2022-133642-I00), IDEATE (AEI-MICINN, PID2022-141566NB-I00), A-BMC (AEI-MICINN, CNS2022-135480), CERCA Programme/Generalitat de Catalunya, and Agencia Nacional de Investigación y Desarrollo de Chile (ANID) (Grant No. FONDECYT INICIACIÓN 11230262). Ricardo Marques acknowledges the support of the Serra Húnter Programme. B. Nagarajan acknowledges the support of FPI Becas, MICINN, Spain . The authors thankfully acknowledge the computer resources at FinisTerrae III and the technical support provided by the Galician Supercomputing Center (CESGA) (RES-IM-2023-2-0025).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

FoodMem: near real-time and precise food video segmentation

  • AlMughrabi, Ahmad
  • Galán, Adrián
  • Marques, Ricardo
  • Radeva, Petia
Food segmentation, including in videos, is vital for addressing real-world health, agriculture, and food biotechnology issues. Current limitations lead to inaccurate nutritional analysis, inefficient crop management, and suboptimal food processing, impacting food security and public health. Improving segmentation techniques can enhance dietary assessments, agricultural productivity, and the food production process. This study introduces the development of a robust framework for high-quality, near-real-time segmentation and tracking of food items in videos, using minimal hardware resources. We present FoodMem, a novel framework designed to segment food items from video sequences of 360-degree unbounded scenes. FoodMem can consistently generate masks of food portions in a video sequence, overcoming the limitations of existing semantic segmentation models, such as flickering and prohibitive inference speeds in video processing contexts. To address these issues, FoodMem leverages a two-phase solution: a transformer segmentation phase to create initial segmentation masks and a memory-based tracking phase to monitor food masks in complex scenes. Our framework outperforms current state-of-the-art food segmentation models, yielding superior performance across various conditions, such as camera angles, lighting, reflections, scene complexity, and food diversity.2This results in reduced segmentation noise, elimination of artifacts, and completion of missing segments. We also introduce a new annotated food dataset encompassing challenging scenarios absent in previous benchmarks. Extensive experiments conducted on MetaFood3D, Nutrition5k, and Vegetables & Fruits datasets demonstrate that FoodMem enhances the state-of-the-art by 2.5% mean average precision in food video segmentation and is faster on average. The source code is available at: 3., This work was partially funded by the EU project MUSAE (No. 01070421), 2021- SGR-01094 (AGAUR), Icrea Academia’2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220- VET000089434, Erasmus+ EU), DeepSense (ACE053/22/000029, ACCIÓ), and Grants PID2022141566NB-I00 (IDEATE), PDC2022-133642-I00 (DeepFoodVol), and CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.13039/501100 011033, by FEDER (UE), and by European Union NextGenerationEU/ PRTR. A. AlMughrabi acknowledges the support of FPI Becas, MICINN, Spain.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

VolE-complete: enhancing food 3D reconstruction and volume estimation with symmetry-guided point cloud completion

  • Haroon, Umair
  • Almughrabi, Ahmad
  • Marques, Ricardo
  • Radeva, Petia
Accurate estimation of food volume is essential for personalised nutrition and health initiatives. However, the challenge of obtaining high-quality 3D reconstructions of food items, especially in the presence of occlusions or limited observations, remains considerable. Our prior framework, VolE, provided a robust foundation for mobile-driven 3D food reconstruction but encountered difficulties with entirely unseen or incomplete object parts, thereby limiting model accuracy and volume estimates. We present VolE-Complete, an advanced framework that incorporates a cutting-edge point cloud completion technique for 3D reconstruction and volume estimation of food. By effectively inferring and reconstructing missing geometric details, VolE-Complete yields more comprehensive and precise 3D representations of food. valuations carried out on the challenging FoodKit and MetaFood3D datasets demonstrate a Mean Absolute Percentage Error (MAPE) of 0.2% and substantially improved reconstruction quality. This development facilitates dependable, mobile-based, and depth-free food volume estimation, thereby enhancing dietary assessments and enabling broader applications. The source code is available at: https://github.com/GCVCG/VolE-Complete., This work was partially funded by the EU project MUSAE (No. 01070421), 2021-SGR-01094 (AGAUR), Icrea Academia-2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220-VET000089434, Erasmus+ EU), DeepSense (ACE053/22/000029, ACCIO), CERCA Programme/Generalitat de Catalunya, and Grants PID2022-141566NB-I00 (IDEATE), PDC2022-133642-I00 (DeepFoodVol), and CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.115039/501100011033, by FEDER (UE), and by European Union NextGenerationEU/PRTR.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Decoding class dynamics in learning with noisy labels

  • Tatjer, Albert
  • Nagarajan, Bhalaji
  • Marques, Ricardo
  • Radeva, Petia
The creation of large-scale datasets annotated by humans inevitably introduces noisy labels, leading to reduced generalization in deep-learning models. Sample selection-based learning with noisy labels is a recent approach that exhibits promising upbeat performance improvements. The selection of clean samples amongst the noisy samples is an important criterion in the learning process of these models. In this work, we delve deeper into the clean-noise split decision and highlight the aspect that effective demarcation of samples would lead to better performance. We identify the Global Noise Conundrum in the existing models, where the distribution of samples is treated globally. We propose a per-class-based local distribution of samples and demonstrate the effectiveness of this approach in having a better clean-noise split. We validate our proposal on several benchmarks — both real and synthetic, and show substantial improvements over different state-of-the-art algorithms. We further propose a new metric, classiness to extend our analysis and highlight the effectiveness of the proposed method. Source code and instructions to reproduce this paper are available at https://github.com/aldakata/CCLM/, This work was partially funded by the EU project MUSAE (No. 01070421), 2021-SGR-01094 (AGAUR), Icrea Academia’2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220-VET-000089434, Erasmus+ EU), DeepSense (ACE053/22/000029, ACCIÓ), CERCA Programme/Generalitat de Catalunya, and Grants PID2022-141566NB-I00 (IDEATE), PDC2022-133642-I00 (DeepFoodVol), and CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.13039/501100011033, by FEDER (UE), and by European Union NextGenerationEU/ PRTR. R. Marques acknowledges the support of the Serra Húnter Programme. B. Nagarajan acknowledges the support of FPI Becas, MICINN, Spain .
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Fast and accurate gaussian process modelling of real-world materials

  • Colom, Arnau
  • Bouville, Christian
  • Pettre, Julien
  • Bouatouch, Kadi
  • Marques, Ricardo
Our goal in this article is to propose a fast and easy to implement BRDF modeling method that provides both accurate and compact representations for all types of BRDF, i.e., isotropic or anisotropic. To achieve this objective, we use a Bayesian regression method with a Gaussian process prior which allows obtaining compact BRDF representations in a purely analytical way. For this purpose, we use a generalzed distance covariance kernel which is much better suited to BRDF features than the usual Gaussian kernel. To speed up the processing, we adapt this method to the specificities of BRDFs through an appropriate input data structure and distribution of observations so as to drastically reduce the problem dimensionality through an efficient factorization method. In this way, all calculations at both fitting and rendering steps are reduced to basic matrix products and the computation of a BRDF representation with our modeling method takes only a few seconds. Furthermore, rather than using a systematic approach as in state-of-the-art methods, the size and complexity of the BRDF representation can be adapted to the application requirements as regards the fitting accuracy and rendering constraints. Besides, our BRDF representation can be easily converted to spherical harmonics expansions, which allows easier integration in usual rendering algorithms. We also propose importance sampling methods derived from our BRDF modeling method that leads to fast and easy implementations. Experimental applications of our method to various types of isotropic and anisotropic BRDFs show that state-of-the-art methods can be outperformed in most cases by using a small set of observations for the regression., This work was partially funded by the Research Consolidation grant CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.13039/501100 011033, by FEDER (UE), and by European Union NextGenerationEU/ PRTR. It has also been partially founded by PID2022141566NB-I00 (IDEATE)..
Repositori Obert UdL
Publicación Artículo científico (JournalArticle)

Enhancing statistical chart accessibility for people with low vision: insights from a user test

  • Alcaraz Martínez, Rubén
  • Ribera, Mireia
  • Adeva‑Fillol, Adrià
  • Pascual Almenara, Afra
A remote user test was performed with two versions (one accessible and one non-accessible) of three types of web-based charts (horizontal bar chart, vertical stacked bar chart, and line chart). The objectives of the test were: (a) to validate a set of heuristic indicators for the evaluation of the accessibility of statistical charts presented in a previous work (Fariñas Falcón et al. in Mediocentro Electrónica 21(1):65–68, 2017); (b) to identify new barriers and preferences for users with low vision in the access and use of this content not previously contemplated. 12 users were tested, with a variety of conditions associated with low vision: low visual acuity (6 users), reduced central vision (2 users), reduced peripheral vision (2 users), blurry vision (1 user), sensitivity to light (3 users), Nystagmus (2 users) and color vision deficiency (CVD) (4 users). From a quantitative standpoint, accessible versions of charts were more efficient, effective, and satisfactory. From a qualitative point of view, results verify the relevance of heuristics H2, Legend; H3, Axes; H6, Data source (as data table); H10, Safe colors; H11, Contrast; H12, Legibility; H13, Image quality; H14, Resize; H16, Focus visible; H17, Independent navigation; related to the proposed tasks. As new observations, tooltips were highly valued by all users, but their implementation must be improved to avoid covering up significant parts of the charts when displayed. The data table has also been frequently used by all users, especially in the non-accessible versions, allowing them to carry out tasks more efficiently. The position and size of the legend can be a significant barrier if it is too small or appears in an unusual position. Finally, despite the limitations related to color perception, some users prefer color graphics to black and white, so, to target all profiles, it is necessary to redundantly encode categories with colors and patterns as well., This work was partially funded by Spanish project PID2022-141566NB-I00 (AEI-MICINN). This work also has been partially supported by the Spanish project PID2022-136436NB-I00 (AEI-MICINN)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Bayesian DivideMix++ for enhanced learning with noisy labels

  • Nagarajan, Bhalaji
  • Marques, Ricardo
  • Aguilar, Eduardo J.
  • Radeva, Petia
Leveraging inexpensive and human intervention-based annotating methodologies, such as crowdsourcing and web crawling, often leads to datasets with noisy labels. Noisy labels can have a detrimental impact on the performance and generalization of deep neural networks. Robust models that are able to handle and mitigate the effect of these noisy labels are thus essential. In this work, we explore the open challenges of neural network memorization and uncertainty in creating robust learning algorithms with noisy labels. To overcome them, we propose a novel framework called “Bayesian DivideMix++” with two critical components: (i) DivideMix++, to enhance the robustness against memorization and (ii) Monte-Carlo MixMatch, which focuses on improving the effectiveness towards label uncertainty. DivideMix++ improves the pipeline by integrating the warm-up and augmentation pipeline with self-supervised pre-training and dedicated different data augmentations for loss analysis and backpropagation. Monte-Carlo MixMatch leverages uncertainty measurements to mitigate the influence of uncertain samples by reducing their weight in the data augmentation MixMatch step. We validate our proposed pipeline using four datasets encompassing various synthetic and real-world noise settings. We demonstrate the effectiveness and merits of our proposed pipeline using extensive experiments. Bayesian DivideMix++ outperforms the state-of-the-art models by considerable differences in all experiments. Our findings underscore the potential of leveraging these modifications to enhance the performance and generalization of deep neural networks in practical scenarios., This work was partially funded by the Horizon EU project MUSAE (No. 01070421), 2021-SGR-01094 (AGAUR), Icrea Academia’2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220-VET-000089434, Erasmus+ EU), DeepSense (ACE053/22/000029, ACCIÓ), DeepFoodVol (AEI-MICINN, PDC2022-133642-I00), IDEATE (AEI-MICINN, PID2022-141566NB-I00), A-BMC (AEI-MICINN, CNS2022-135480), CERCA Programme/Generalitat de Catalunya, and Agencia Nacional de Investigación y Desarrollo de Chile (ANID) (Grant No. FONDECYT INICIACIÓN 11230262). Ricardo Marques acknowledges the support of the Serra Húnter Programme. B. Nagarajan acknowledges the support of FPI Becas, MICINN, Spain . The authors thankfully acknowledge the computer resources at FinisTerrae III and the technical support provided by the Galician Supercomputing Center (CESGA) (RES-IM-2023-2-0025).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Decoding class dynamics in learning with noisy labels

  • Tatjer, Albert
  • Nagarajan, Bhalaji
  • Marques, Ricardo
  • Radeva, Petia
The creation of large-scale datasets annotated by humans inevitably introduces noisy labels, leading to reduced generalization in deep-learning models. Sample selection-based learning with noisy labels is a recent approach that exhibits promising upbeat performance improvements. The selection of clean samples amongst the noisy samples is an important criterion in the learning process of these models. In this work, we delve deeper into the clean-noise split decision and highlight the aspect that effective demarcation of samples would lead to better performance. We identify the Global Noise Conundrum in the existing models, where the distribution of samples is treated globally. We propose a per-class-based local distribution of samples and demonstrate the effectiveness of this approach in having a better clean-noise split. We validate our proposal on several benchmarks — both real and synthetic, and show substantial improvements over different state-of-the-art algorithms. We further propose a new metric, classiness to extend our analysis and highlight the effectiveness of the proposed method. Source code and instructions to reproduce this paper are available at https://github.com/aldakata/CCLM/, This work was partially funded by the EU project MUSAE (No. 01070421), 2021-SGR-01094 (AGAUR), Icrea Academia’2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220-VET-000089434, Erasmus+ EU), DeepSense (ACE053/22/000029, ACCIÓ), CERCA Programme/Generalitat de Catalunya, and Grants PID2022-141566NB-I00 (IDEATE), PDC2022-133642-I00 (DeepFoodVol), and CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.13039/501100011033, by FEDER (UE), and by European Union NextGenerationEU/ PRTR. R. Marques acknowledges the support of the Serra Húnter Programme. B. Nagarajan acknowledges the support of FPI Becas, MICINN, Spain .
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Fast and accurate gaussian process modelling of real-world materials

  • Colom, Arnau
  • Bouville, Christian
  • Pettre, Julien
  • Bouatouch, Kadi
  • Marques, Ricardo
Our goal in this article is to propose a fast and easy to implement BRDF modeling method that provides both accurate and compact representations for all types of BRDF, i.e., isotropic or anisotropic. To achieve this objective, we use a Bayesian regression method with a Gaussian process prior which allows obtaining compact BRDF representations in a purely analytical way. For this purpose, we use a generalzed distance covariance kernel which is much better suited to BRDF features than the usual Gaussian kernel. To speed up the processing, we adapt this method to the specificities of BRDFs through an appropriate input data structure and distribution of observations so as to drastically reduce the problem dimensionality through an efficient factorization method. In this way, all calculations at both fitting and rendering steps are reduced to basic matrix products and the computation of a BRDF representation with our modeling method takes only a few seconds. Furthermore, rather than using a systematic approach as in state-of-the-art methods, the size and complexity of the BRDF representation can be adapted to the application requirements as regards the fitting accuracy and rendering constraints. Besides, our BRDF representation can be easily converted to spherical harmonics expansions, which allows easier integration in usual rendering algorithms. We also propose importance sampling methods derived from our BRDF modeling method that leads to fast and easy implementations. Experimental applications of our method to various types of isotropic and anisotropic BRDFs show that state-of-the-art methods can be outperformed in most cases by using a small set of observations for the regression., This work was partially funded by the Research Consolidation grant CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.13039/501100 011033, by FEDER (UE), and by European Union NextGenerationEU/ PRTR. It has also been partially founded by PID2022141566NB-I00 (IDEATE)..
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

FoodMem: near real-time and precise food video segmentation

  • AlMughrabi, Ahmad
  • Galán, Adrián
  • Marques, Ricardo
  • Radeva, Petia
Food segmentation, including in videos, is vital for addressing real-world health, agriculture, and food biotechnology issues. Current limitations lead to inaccurate nutritional analysis, inefficient crop management, and suboptimal food processing, impacting food security and public health. Improving segmentation techniques can enhance dietary assessments, agricultural productivity, and the food production process. This study introduces the development of a robust framework for high-quality, near-real-time segmentation and tracking of food items in videos, using minimal hardware resources. We present FoodMem, a novel framework designed to segment food items from video sequences of 360-degree unbounded scenes. FoodMem can consistently generate masks of food portions in a video sequence, overcoming the limitations of existing semantic segmentation models, such as flickering and prohibitive inference speeds in video processing contexts. To address these issues, FoodMem leverages a two-phase solution: a transformer segmentation phase to create initial segmentation masks and a memory-based tracking phase to monitor food masks in complex scenes. Our framework outperforms current state-of-the-art food segmentation models, yielding superior performance across various conditions, such as camera angles, lighting, reflections, scene complexity, and food diversity.2This results in reduced segmentation noise, elimination of artifacts, and completion of missing segments. We also introduce a new annotated food dataset encompassing challenging scenarios absent in previous benchmarks. Extensive experiments conducted on MetaFood3D, Nutrition5k, and Vegetables & Fruits datasets demonstrate that FoodMem enhances the state-of-the-art by 2.5% mean average precision in food video segmentation and is faster on average. The source code is available at: 3., This work was partially funded by the EU project MUSAE (No. 01070421), 2021- SGR-01094 (AGAUR), Icrea Academia’2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220- VET000089434, Erasmus+ EU), DeepSense (ACE053/22/000029, ACCIÓ), and Grants PID2022141566NB-I00 (IDEATE), PDC2022-133642-I00 (DeepFoodVol), and CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.13039/501100 011033, by FEDER (UE), and by European Union NextGenerationEU/ PRTR. A. AlMughrabi acknowledges the support of FPI Becas, MICINN, Spain.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Enhancing statistical chart accessibility for people with low vision: insights from a user test

  • Alcaraz Martínez, Rubén
  • Ribera, Mireia
  • Adeva‑Fillol, Adrià
  • Pascual Almenara, Afra
A remote user test was performed with two versions (one accessible and one non-accessible) of three types of web-based charts (horizontal bar chart, vertical stacked bar chart, and line chart). The objectives of the test were: (a) to validate a set of heuristic indicators for the evaluation of the accessibility of statistical charts presented in a previous work (Fariñas Falcón et al. in Mediocentro Electrónica 21(1):65–68, 2017); (b) to identify new barriers and preferences for users with low vision in the access and use of this content not previously contemplated. 12 users were tested, with a variety of conditions associated with low vision: low visual acuity (6 users), reduced central vision (2 users), reduced peripheral vision (2 users), blurry vision (1 user), sensitivity to light (3 users), Nystagmus (2 users) and color vision deficiency (CVD) (4 users). From a quantitative standpoint, accessible versions of charts were more efficient, effective, and satisfactory. From a qualitative point of view, results verify the relevance of heuristics H2, Legend; H3, Axes; H6, Data source (as data table); H10, Safe colors; H11, Contrast; H12, Legibility; H13, Image quality; H14, Resize; H16, Focus visible; H17, Independent navigation; related to the proposed tasks. As new observations, tooltips were highly valued by all users, but their implementation must be improved to avoid covering up significant parts of the charts when displayed. The data table has also been frequently used by all users, especially in the non-accessible versions, allowing them to carry out tasks more efficiently. The position and size of the legend can be a significant barrier if it is too small or appears in an unusual position. Finally, despite the limitations related to color perception, some users prefer color graphics to black and white, so, to target all profiles, it is necessary to redundantly encode categories with colors and patterns as well., This work was partially funded by Spanish project PID2022-141566NB-I00 (AEI-MICINN). This work also has been partially supported by the Spanish project PID2022-136436NB-I00 (AEI-MICINN)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

VolE-complete: enhancing food 3D reconstruction and volume estimation with symmetry-guided point cloud completion

  • Haroon, Umair
  • Almughrabi, Ahmad
  • Marques, Ricardo
  • Radeva, Petia
Accurate estimation of food volume is essential for personalised nutrition and health initiatives. However, the challenge of obtaining high-quality 3D reconstructions of food items, especially in the presence of occlusions or limited observations, remains considerable. Our prior framework, VolE, provided a robust foundation for mobile-driven 3D food reconstruction but encountered difficulties with entirely unseen or incomplete object parts, thereby limiting model accuracy and volume estimates. We present VolE-Complete, an advanced framework that incorporates a cutting-edge point cloud completion technique for 3D reconstruction and volume estimation of food. By effectively inferring and reconstructing missing geometric details, VolE-Complete yields more comprehensive and precise 3D representations of food. valuations carried out on the challenging FoodKit and MetaFood3D datasets demonstrate a Mean Absolute Percentage Error (MAPE) of 0.2% and substantially improved reconstruction quality. This development facilitates dependable, mobile-based, and depth-free food volume estimation, thereby enhancing dietary assessments and enabling broader applications. The source code is available at: https://github.com/GCVCG/VolE-Complete., This work was partially funded by the EU project MUSAE (No. 01070421), 2021-SGR-01094 (AGAUR), Icrea Academia-2022 (Generalitat de Catalunya), Robo STEAM (2022-1-BG01-KA220-VET000089434, Erasmus+ EU), DeepSense (ACE053/22/000029, ACCIO), CERCA Programme/Generalitat de Catalunya, and Grants PID2022-141566NB-I00 (IDEATE), PDC2022-133642-I00 (DeepFoodVol), and CNS2022-135480 (A-BMC) funded by MICIU/AEI/10.115039/501100011033, by FEDER (UE), and by European Union NextGenerationEU/PRTR.