Amazon Berkeley Objects

Indoor environment and object dataset based on Amazon product listings

Released in: ABO: Dataset and Benchmarks for Real-World 3D Object Understanding



Amazon Berkeley Objects (ABO) is a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, household objects. The authors derive challenging benchmarks that exploit the unique properties of ABO and measure the current limits of the state-of-the-art on three open problems for real-world 3D object understanding: single-view 3D reconstruction, material estimation, and cross-domain multi-view object retrieval.

150K listings of 576 product types, 8000 handmade high-quality 3D models

Images in dataset


Year Released

Key Links & Stats

@article{collins2022abo, title={ABO: Dataset and Benchmarks for Real-World 3D Object Understanding}, author={Collins, Jasmine and Goel, Shubham and Deng, Kenan and Luthra, Achleshwar and Xu, Leon and Gundogdu, Erhan and Zhang, Xi and Yago Vicente, Tomas F and Dideriksen, Thomas and Arora, Himanshu and Guillaumin, Matthieu and Malik, Jitendra}, journal={CVPR}, year={2022} }



  1. Still Image
  2. 3D Asset


  1. Home/Office

ML Task

  1. General
  2. Object Detection
  3. Semantic Segmentation
  4. Instance Segmentation
  5. Object Recognition
  6. Scene Understanding

Related organizations