OASIS: A Large-Scale Dataset for Single Image 3D in the Wild
Weifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima, Max Hamilton, Jia Deng
Abstract
Single-view 3D is the task of recovering 3D properties such as depth and surface normals from a single image. We hypothesize that a major obstacle to single-image 3D is data. We address this issue by presenting Open Annotations of Single Image Surfaces (OASIS), a dataset for single-image 3D in the wild consisting of annotations of detailed 3D geometry for 140,000 images. We train and evaluate leading models on a variety of single-image 3D tasks. We expect OASIS to be a useful resource for 3D vision research. Project site: https://pvl.cs.princeton.edu/OASIS.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 6b249f7a-7b2b-422f-9ff4-b3cad3759c20Cited by top-tier papers32
- Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D ScansAinaz Eftekhar, Alexander Sax, Jitendra Malik, Amir ZamirICCV 2021 · 422 citations
- Metric3D: Towards Zero-shot Metric 3D Prediction from A Single ImageWei Yin, Chi Zhang, Hao Chen, Zhipeng Cai et al.ICCV 2023 · 388 citations
- 4M: Massively Multimodal Masked ModelingDavid Mizrahi, Roman Bachmann, Oguzhan Fatih Kar, Teresa Yeo et al.NeurIPS 2023 · 154 citations
- 3D Common Corruptions and Data AugmentationOguzhan Fatih Kar, Teresa Yeo, Andrei Atanov, Amir ZamirCVPR 2022 · 80 citations
- Hierarchical Normalization for Robust Monocular Depth EstimationChi Zhang, Wei Yin, Billzb Wang, Gang Yu et al.NeurIPS 2022 · 73 citations
Related papers
- MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training SupervisionRuicheng Wang, Sicheng Xu, Cassie Dai, Jianfeng Xiang et al.CVPR 2025
- ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-Based ConsistencyZixuan Huang, Varun Jampani, Anh Thai, Yuanzhen Li et al.CVPR 2023
- ABO: Dataset and Benchmarks for Real-World 3D Object UnderstandingJasmine Collins, Shubham Goel, Kenan Deng, Achleshwar Luthra et al.CVPR 2022 · 117 citations
- Reconstructing In-the-Wild Open-Vocabulary Human-Object InteractionsBoran Wen, Dingbang Huang, Zichen Zhang, Jiahong Zhou et al.CVPR 2025
- SiM3D: Single-Instance Multiview Multimodal and Multisetup 3D Anomaly Detection BenchmarkAlex Costanzino, Pierluigi Zama Ramirez, Luigi Lella, Matteo Ragaglia et al.ICCV 2025 · 2 citations
