Saved in:
Bibliographic Details
Main Authors: Cui, Yangzhi, Qiao, Feng, Jacobs, Nathan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.23237
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917523100794880
author Cui, Yangzhi
Qiao, Feng
Jacobs, Nathan
author_facet Cui, Yangzhi
Qiao, Feng
Jacobs, Nathan
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2605_23237
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle StereoGenBench: A Synthetic Multi-Camera Benchmark for Stereo Generation under Controlled Baseline Regimes
Cui, Yangzhi
Qiao, Feng
Jacobs, Nathan
Computer Vision and Pattern Recognition
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
title StereoGenBench: A Synthetic Multi-Camera Benchmark for Stereo Generation under Controlled Baseline Regimes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.23237