# Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset

arXiv: https://arxiv.org/abs/2003.11172 · HTML: https://mlsanity.com/paper/2003.11172/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2020.

## Built on by (most cited first, 30 of 36)

- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [Hierarchical Normalization for Robust Monocular Depth Estimation](https://mlsanity.com/paper/2210.09670/) (2022)
- [RGB-D Saliency Detection via Cascaded Mutual Information Minimization](https://mlsanity.com/paper/2109.07246/) (2021)
- [3D generation on ImageNet](https://mlsanity.com/paper/2303.01416/) (2023)
- [Toward Practical Monocular Indoor Depth Estimation](https://mlsanity.com/paper/2112.02306/) (2021)
- [Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image](https://mlsanity.com/paper/2208.13241/) (2022)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [The Second Monocular Depth Estimation Challenge](https://mlsanity.com/paper/2304.07051/) (2023)
- [A Survey on RGB-D Datasets](https://mlsanity.com/paper/2201.05761/) (2022)
- [Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth](https://mlsanity.com/paper/2202.01470/) (2022)
- [Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings](https://mlsanity.com/paper/2202.02002/) (2022)
- [Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data](https://mlsanity.com/paper/2306.02878/) (2023)
- [Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering](https://mlsanity.com/paper/2309.09724/) (2023)
- [From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection](https://mlsanity.com/paper/2511.00181/) (2025)
- [Impact of Pseudo Depth on Open World Object Segmentation with Minimal User Guidance](https://mlsanity.com/paper/2304.05716/) (2023)
- [Scale-Invariant Monocular Depth Estimation via SSI Depth](https://mlsanity.com/paper/2406.09374/) (2024)
- [Self-Distilled Depth Refinement with Noisy Poisson Fusion](https://mlsanity.com/paper/2409.17880/) (2024)
- [Consistency-aware Self-Training for Iterative-based Stereo Matching](https://mlsanity.com/paper/2503.23747/) (2025)
- [Lite Any Stereo: Efficient Zero-Shot Stereo Matching](https://mlsanity.com/paper/2511.16555/) (2025)
- [ReShader: View-Dependent Highlights for Single Image View-Synthesis](https://mlsanity.com/paper/2309.10689/) (2023)
- [What Makes for a Good Stereoscopic Image?](https://mlsanity.com/paper/2412.21127/) (2024)
- [DiffStereo: High-Frequency Aware Diffusion Model for Stereo Image Restoration](https://mlsanity.com/paper/2501.10325/) (2025)
- [One Look is Enough: Seamless Patchwise Refinement for Zero-Shot Monocular Depth Estimation on High-Resolution Images](https://mlsanity.com/paper/2503.22351/) (2025)
- [Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards](https://mlsanity.com/paper/2506.05367/) (2025)
- [FCDSN-DC: An Accurate and Lightweight Convolutional Neural Network for Stereo Estimation with Depth Completion](https://mlsanity.com/paper/2209.06525/) (2022)
- [BS3D: Building-scale 3D Reconstruction from RGB-D Images](https://mlsanity.com/paper/2301.01057/) (2023)
- [SNNSIR: A Simple Spiking Neural Network for Stereo Image Restoration](https://mlsanity.com/paper/2508.12271/) (2025)
- [ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device](https://mlsanity.com/paper/2607.08771/) (2026)
- [DepthART: Scaling Foundation Monocular Depth to Tiny Models](https://mlsanity.com/paper/2607.17099/) (2026)
- [PlantStereo: A Stereo Matching Benchmark for Plant Surface Dense Reconstruction](https://mlsanity.com/paper/2111.15192/) (2021)

## Abstract (arXiv)

With the mass-market adoption of dual-camera mobile phones, leveraging stereo information in computer vision has become increasingly important. Current state-of-the-art methods utilize learning-based algorithms, where the amount and quality of training samples heavily influence results. Existing stereo image datasets are limited either in size or subject variety. Hence, algorithms trained on such datasets do not generalize well to scenarios encountered in mobile photography. We present Holopix50k, a novel in-the-wild stereo image dataset, comprising 49,368 image pairs contributed by users of the Holopix mobile social platform. In this work, we describe our data collection process and statistically compare our dataset to other popular stereo datasets. We experimentally show that using our dataset significantly improves results for tasks such as stereo super-resolution and self-supervised monocular depth estimation. Finally, we showcase practical applications of our dataset to motivate novel works and use cases. The Holopix50k dataset is available at http://github.com/leiainc/holopix50k