cs.CVMay 22, 2026

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

Authors: Yangzhi Cui, Feng Qiao, Nathan Jacobs

Organizations: Washington University in St. Louis

Abstract

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

Explore similar work

CardsList
Apr 6, 2026cs.CV

SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo

Generating procedural synthetic data for multi-view stereo (MVS) usually requires writing complex rules to match the realism of curated datasets. We demonstrate that we can generate effective training data using SimpleProc: a new, fully procedural generator driven by a very small set of rules based on Non-Uniform Rational Basis Splines (NURBS), as well as simple displacement and texture patterns. At a modest scale of 8,000 images, our approach achieves superior results compared to manually curated images at the same scale sourced from games and real-world objects. When scaled to 352,000 images, our approach achieves similar, and in some benchmarks, even better results than the current state-of-the-art trained on over 692,000 manually curated images. The source code and the data are available at https://github.com/princeton-vl/SimpleProc.
Zeyu Ma, Alexander Raistrick, Jia Deng
Multi-ViewSynthetic DataEasyB-Spline
AskPDF
Jun 12, 2026cs.CV

StereoGeo: an end-to-end stereo camera calibration method

In this work, we propose StereoGeo, an end-to-end network-based approach for stereo camera calibration. Our method estimates the focal lengths and gravity directions of the left and right cameras, as well as the relative extrinsic transformation relating them. Existing methods often rely on calibration patterns in structured environments or address only a single camera configuration, being limited to either intrinsic or extrinsic estimation, and depending on a multi-view setups. StereoGeo extends the GeoCalib algorithm, integrating deep neural network feature extraction with a differentiable optimizer. Extensive experiments on real-world benchmarks demonstrate that StereoGeo achieves competitive performance for intrinsic calibration and provides accurate stereo extrinsic estimation, outperforming existing methods that are limited to monocular settings. The dataset used in this work is partially publicly available at https://github.com/meddourimane/StereoGeo-dataset.
Imane Meddour, Andréa Macario Barros, Cédric Gouy-Pailler
Camera IntrinsicsStereo VisionFeed-Forward Visual Geometry Estimation
AskPDF
Jun 24, 2026cs.CV

Cross-View Variance Correlation in Path-Traced Stereo:A Hidden Shortcut in Synthetic Training Data

Path-traced synthetic stereo data underlie a large fraction of modern disparity-estimation training pipelines. We report a previously unrecognised property of such data: while the Monte Carlo (MC) noise streams of the two cameras are statistically independent, the underlying \emph{variance fields} -- deterministic per-pixel functions of the rendering integrand -- are highly correlated once aligned by the ground-truth disparity warp. Across 20 scenes rendered with Mitsuba~3, the warped Pearson correlation reaches ρ=0.754±0.016ρ{=}0.754{\pm}0.016 across 20 scenes at SPP=512\mathrm{SPP}{=}512, and on a representative scene remains essentially invariant (ρ=0.778±0.001ρ{=}0.778{\pm}0.001) over a 16×16\times range of samples per pixel. The effect is strongest in Lambertian regions (ρ≈0.78ρ{\approx}0.78) and substantially weaker in glass (ρ≈0.30ρ{\approx}0.30), as predicted by an integrand decomposition into view-independent and view-dependent components. A residual-shuffle intervention that breaks the cross-view alignment while preserving the clean image degrades the GT cost margin by 33%33\% on non-glass and the variance-based winner-take-all accuracy on glass by 4.3×4.3\times, confirming the structure functions as a matching cue. This signal is unique to MC-rendered data and constitutes a candidate sim-to-real shortcut whose impact on trained networks remains to be quantified.
Po-Ting Lin
Stereo VisionCross-ViewPixel-Level PredictionSynthetic Training DataSpearman CorrelationShortcuts+1
AskPDF