NutriVision: Ingredient-Conditioned Fusion and Prediction for Single-Image Food Nutrition Estimation

arXiv:2609.33076 · cs.CV, cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Project page: https://kianraj.github.io/nutrivision

Terminology

• Ablation — 19× in this paper · explained in 1 episode
• Alignment — 11× in this paper · explained in 1 episode
• Embeddings — 6× in this paper · explained in 2 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Frequency-Aligned Fusion Module — 4× in this paper
• Scale-Shift Residual Adapter — 4× in this paper
• Aggregation — 3× in this paper · explained in 1 episode
• Mask-based Prediction Head — 3× in this paper
• Multimodal Fusion — 3× in this paper · explained in 3 episodes
• Scaffolding — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Ingredient-Aware Mask-based Prediction Head — 2× in this paper
• Robustness — 2× in this paper · explained in 5 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Distribution Shift — 1× in this paper · explained in 6 episodes
• Dynamic Position Encoding — 1× in this paper
• Feature Extraction — 1× in this paper · explained in 2 episodes
• Feature Selection — 1× in this paper · explained in 4 episodes
• Fine-Grained Modelling — 1× in this paper
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Ingredient-Conditioned Frequency-Aligned Fusion Module — 1× in this paper
• Ingredient-aware Spatial Mixer — 1× in this paper
• Loss Function — 1× in this paper · explained in 2 episodes
• Percentage Mean Absolute Error — 1× in this paper
• Positional Bias — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• Depth Anything 3: Recovering the Visual Space from Any Views

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models