Datasets
ImageNet3D Dataset
We present ImageNet3D, a large dataset for general-purpose object-level 3D understanding. ImageNet3D augments 200 categories from the ImageNet dataset with 2D bounding box, 3D pose, 3D location annotations, and image captions interleaved with 3D information. With the new annotations available in ImageNet3D, we could (i) analyze the object-level 3D awareness of visual foundation models, (ii) study and develop general-purpose models that infer both 2D and 3D information for arbitrary rigid objects in natural images, and (iii) integrate unified 3D models with large language models for 3D-related reasoning. We consider two new tasks, probing of object-level 3D awareness and open vocabulary pose estimation, besides standard classification and pose estimation.
AbdomenAtlas 1.0 [News]
A substantial multi-organ dataset with the spleen, liver, kidneys, stomach, gallbladder, pancreas, aorta, and postcava per-voxel annotated in 5,195 CT volumes, totaling 1.5 million CT slices collected from 26 hospitals.
PASCAL Part Segmentation Challenge
We provide a platform on which researchers can investigate the performance of semantic part segmentation methods on challenging PASCAL VOC dataset. We build a benchmark, together with an evaluate server. The benchmark currently uses 7 articulated categories.
PASCAL-S Dataset
Free-fiewing fixations on a subset of 850 images from PASCAL VOC. Collected on 8 subjects, 3s viewing time, Eyelink II eye tracker. The performance of most algorithms suggest that PASCAL-S is less biased than most of the saliency datasets.
PASCAL-Part Dataset
This dataset is a set of additional annotations for PASCAL VOC 2010. It goes beyond the original PASCAL object detection task by providing segmentation masks for each body part of the object. For categories that do not have a consistent set of parts (e.g., boat), we provide the silhouette annotation.
PASCAL-Context Dataset
This dataset is a set of additional annotations for PASCAL VOC 2010. It goes beyond the original PASCAL semantic segmentation task by providing annotations for the whole scene (with 400+ labels). Every pixel has a unique class label. Instance information (i.e, different masks to separate different instances of the same class in the same image) are currently provided for the 20 PASCAL objects.