V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos

ArXi:2604.11913v1 Announce Type: new Nutrition estimation of meals from visual data is an important problem for dietary monitoring and computational health, but existing approaches largely rely on single images of the finally completed dish. This setting is fundamentally limited because many nutritionally relevant ingredients and transformations, such as oils, sauces, and mixed components, become visually ambiguous after cooking, making accurate calorie and macronutrient estimation difficult.