# StereoGenBench: A Synthetic Multi-Camera Benchmark for Stereo Generation under Controlled Baseline Regimes

arXiv: https://arxiv.org/abs/2605.23237 · HTML: https://mlsanity.com/paper/2605.23237/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 22 May 2026.

## Builds on (most cited first, 26 of 26)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [3D Photography using Context-aware Layered Depth Inpainting](https://mlsanity.com/paper/2004.04727/) (2020)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo](https://mlsanity.com/paper/2303.01943/) (2023)
- [DynamicStereo: Consistent Dynamic Depth from Stereo Videos](https://mlsanity.com/paper/2305.02296/) (2023)
- [Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos](https://mlsanity.com/paper/2412.09621/) (2024)
- [Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks](https://mlsanity.com/paper/1604.03650/) (2016)
- [DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching](https://mlsanity.com/paper/2308.08479/) (2023)
- [Learning Stereo from Single Images](https://mlsanity.com/paper/2008.01484/) (2020)
- [StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos](https://mlsanity.com/paper/2409.07447/) (2024)
- [Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset](https://mlsanity.com/paper/2003.11172/) (2020)
- [SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix](https://mlsanity.com/paper/2407.00367/) (2024)
- [ZeroStereo: Zero-shot Stereo Matching from Single Images](https://mlsanity.com/paper/2501.08654/) (2025)
- [Match Stereo Videos via Bidirectional Alignment](https://mlsanity.com/paper/2409.20283/) (2024)
- [Mono2Stereo: A Benchmark and Empirical Study for Stereo Conversion](https://mlsanity.com/paper/2503.22262/) (2025)
- [M2SVid: End-to-End Inpainting and Refinement for Monocular-to-Stereo Video Conversion](https://mlsanity.com/paper/2505.16565/) (2025)
- [Towards Open-World Generation of Stereo Images and Unsupervised Matching](https://mlsanity.com/paper/2503.12720/) (2025)
- [Active-Passive SimStereo -- Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo Methods](https://mlsanity.com/paper/2209.08305/) (2022)
- [DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation](https://mlsanity.com/paper/2508.13091/) (2025)
- [Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding](https://mlsanity.com/paper/2512.14236/) (2025)
- [StereoPilot: Learning Unified and Efficient Stereo Conversion via Generative Priors](https://mlsanity.com/paper/2512.16915/) (2025)
- [Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards](https://mlsanity.com/paper/2506.05367/) (2025)
- [StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space](https://mlsanity.com/paper/2512.10959/) (2025)

## Abstract (arXiv)

Stereo image and video generation, stereo geometry estimation, and condition-controlled view synthesis require paired data in which the variables that determine binocular geometry -- camera baseline, intrinsics, scene depth, and camera motion -- are known and controllable. Existing stereo resources provide subsets of these variables, but resources commonly used for stereo generation evaluation do not, to our knowledge, provide scene-paired, calibrated multi-baseline right-view ground truth with jointly recorded intrinsics, dense metric depth, and per-frame poses in a single controlled source. We introduce StereoGenBench, a synthetic Unreal Engine benchmark designed to make baseline-regime sensitivity and target-camera consistency measurable under matched scene content. Each scene is rendered with a rigid six-camera lateral array, yielding up to 15 calibrated view pairs; adjacent baselines are sampled from inter-pupillary to wide-baseline regimes; focal length is sampled independently; and every view is released with RGB, metric depth, intrinsics, per-pair baselines, and per-frame poses. The splits include two evaluation families for narrow and wide baseline regimes and a train-only family for broader all-pairs coverage. We release the dataset, evaluation code, reference results, Croissant metadata, and generation code/configuration for extension with compatible assets. The dataset is available at https://huggingface.co/datasets/stereo-dataset/stereo-dataset