Research map / 3D vision / Depth and stereo
OmniFood8K: Single-Image Nutrition Estimation via Hierarchical Frequency-Aligned Fusion
Dongjian Yu, Weiqing Min, Qian Jiang, Xing Lin, Xin Jin, Shuqiang Jiang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add FAFM frequency-domain fusion (ablation) | Baseline · Nutrition5k | Mean PMAE: 17.9 -> 17.0 | Improved |
| add SSRA depth adapter (ablation) | Baseline + FAFM · Nutrition5k | Mean PMAE: 17.0 -> 16.8 | Improved |
| add MPH mask-based head (ablation) | Baseline + FAFM + SSRA · Nutrition5k | Mean PMAE: 16.8 -> 16.5 | Improved |
| add SSRA depth adapter (ablation) | Baseline + FAFM · Nutrition5k | Fat PMAE: 21.7 -> 21.9 | Hurt |
| add SSRA depth adapter (ablation) | Baseline + FAFM · Nutrition5k | Mass PMAE: 10.2 -> 10.4 | Hurt |
| add FAFM frequency-domain fusion (ablation) | Baseline · Nutrition5k | Mass PMAE: 11.3 -> 10.2 | Improved |
| add MPH mask-based head (ablation) | Baseline + FAFM + SSRA · Nutrition5k | Fat PMAE: 21.9 -> 21.0 | Improved |
| pretrain on NutritionSynth-115K | Ours · OmniFood8K | Mean PMAE: 8.6 -> 7.8 | Improved |
| pretrain on NutritionSynth-115K | Ours · OmniFood8K | Protein PMAE: 12.6 -> 10.0 | Improved |
| pretrain on NutritionSynth-115K | Ours · OmniFood8K | Mass PMAE: 4.5 -> 4.5 | No clear effect |
| use single RGB image instead of RGB-D input | Ours vs FBFPN · Nutrition5k | Mean PMAE: 17.3 -> 16.5 | Improved |
Closest papers by meaning
- Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food (CVPR 2021 · similarity 0.90)
- Large Scale Visual Food Recognition (TPAMI 2023 · similarity 0.88)
- NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal Descriptions (ICLR 2025 · similarity 0.86)
- OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation (CVPR 2024 · similarity 0.85)
- MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model (CVPR 2020 · similarity 0.83)
- Pic2Prep: A Multimodal Conversational Agent for Cooking Assistance (AAAI 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
