ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
By Jasmine Collins, Shubham Goel, Achleshwar Luthra, Leon L. Xu, Kenan Deng, Xi Zhang, Tomas F. Yago Vicente, Himanshu Arora, T. Dideriksen, Matthieu Guillaumin and 1 more. Computer Vision and Pattern Recognition, 2021
412 citations recorded by the source corpus.
We introduce Amazon Berkeley Objects (ABO), 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 com-plex geometries and physically-based materials that cor-respond to real, household objects. We 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.
Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geology
View Paper: https://www.semanticscholar.org/paper/28fa2c85f891d4d22589d7a63f2c3a62bcb7b136
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Mechanics
- Kwang Moo Yi
- Kalyan Sunkavalli
- S. Gadre
- Sara Sabour
- Ali Farhadi
- Jordi Salvador
- Ludwig Schmidt
- Yilun Du
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jitendra Malik
- Ming-Hsuan Yang
- Dacheng Tao
- Trevor Darrell
- Andrea Vedaldi
- Xiaogang Wang
- Andrew Zisserman
In Geology
- Sara Sabour
- Ali Farhadi
- Yilun Du
- Andrea Tagliasacchi
- Carl Vondrick
- Georgia Gkioxari
- Nanxuan Zhao
- Kalyan Sunkavalli
Citations in the corpus
- Objaverse-XL: A Universe of 10M+ 3D Objects (2023, background): “More recently, IKEA [20] 219 GSO [21] 1K EGAD [22] 2K OmniObject3D [23] 6K PhotoShape [24] 5K ABO [25] 8K Thingi10K [26] 10K 3d-Future [27] 10K ShapeNet [13] 51K Objaverse 1.0 [14] 800K Objaverse-XL 10.2M Segment Anything (SAM) [28] introduced a dataset of one billion object masks used to train a…”
- Structured 3D Latents for Scalable and Versatile 3D Generation (2024, neutral): “ABO [5].”
- Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation (2025, neutral): “From 3Dscanrep [18, 44, 93] to ShapeNet [8], the growth of 3D datasets has been gradual [85, 123, 25, 77, 103, 21, 17].”
- ProcTHOR: Large-Scale Embodied AI Using Procedural Generation (2022, background): “Additionally, we plan to scale up our asset databases by leveraging many open-source 3D asset databases, such as ABO [26], PartNet [81], ShapeNet [15], Google Scanned Objects [30], and CO3D [97], among others.”
- GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting (2024, methodology): “We evaluate our model on two 3D object datasets including the full Google Scanned Objects (GSO) [21] that contains 1009 objects and the Amazon Berkeley Objects (ABO) [17] dataset from which we sample 1000 objects.”
- Kubric: A scalable dataset generator (2022, methodology): “We also plan to preprocess and unify assets from more sources, including the ABC dataset [51] or Amazon Berkeley Objects [17].”
- LRM: Large Reconstruction Model for Single Image to 3D (2023, positive): “To evaluate the performance of LRM on arbitrary images, we collected novel images from Ob-javerse (Deitke et al., 2023), MvImgNet (Yu et al., 2023), ImageNet (Deng et al., 2009), Google Scanned Objects (Downs et al., 2022), Amazon Berkeley Objects (Collins et al., 2022), captured new images in the r”