<- Back to Datasets

StanfordExtra

12k labelled instances of dogs in-the-wild with 2D keypoint and segmentations

StanfordExtra

We introduce an automatic, end-to-end method for recovering the 3D pose and shape of dogs from monocular internet images. The large variation in shape between dog breeds, significant occlusion and low quality of internet images makes this a challenging problem. We learn a richer prior over shapes than previous work, which helps regularize parameter estimation. We demonstrate results on the Stanford Dog dataset, an 'in the wild' dataset of 20,580 dog images for which we have collected 2D joint and silhouette annotations to split for training and evaluation. In order to capture the large shape variety of dogs, we show that the natural variation in the 2D dataset is enough to learn a detailed 3D prior through expectation maximization (EM). As a by-product of training, we generate a new parameterized model (including limb scaling) SMBLD which we release alongside our new annotation dataset StanfordExtra to the research community.

View this Dataset
->
Task
3D Reconstruction / Photogrammetry
Annotation Types
20580
Items
1500
Classes
20580
Labels
Models using this dataset
Last updated on 
January 20, 2022
Licensed under 
CC-BY-NC-SA
Label your own datasets on V7
Try our trial or talk to one of our experts.