{"slug": "a-camera-native-stereo-vr180-dataset", "title": "A Camera-Native Stereo VR180 Dataset", "summary": "Researchers released a camera-native stereo VR180 dataset of 1,211 samples captured with two Blackmagic URSA Cine Immersive cameras, comprising 636 stereo video clips (2,220.8 seconds, mostly 90 fps) and 575 stereo stills, published on Hugging Face with conversion tools on GitHub. Each sample is released as Blackmagic RAW, separate-eye native fisheye HEVC (8160x7200 per eye) and half-equirectangular HEVC (7200x7200 per eye), along with factory lens calibration and AI-generated scene and visual-challenge annotations. Re-encoding 24 clips with x265 across both eyes, four rate points and nine viewing directions, the authors found native-fisheye coding required more bitrate than half-equirectangular coding at equal viewport quality for all 24 clips, with a median increase of 38%.", "body_md": "arXiv:2610.10607v1 Announce Type: new \nAbstract: Immersive VR180 video is increasingly produced with professional stereo fisheye cameras, yet public VR180 research resources are mostly collected from online platforms such as YouTube: already stitched, projected and compressed by unknown pipelines, and without lens calibration. We present a firsthand-captured stereo VR180 dataset recorded with two Blackmagic URSA Cine Immersive cameras. It contains 1,211 samples -- 636 stereo video clips (2,220.8 s, mostly 90 fps) and 575 stereo stills -- each released as camera-native Blackmagic RAW, separate-eye native fisheye HEVC (8160x7200 per eye) and half-equirectangular HEVC (7200x7200 per eye), together with the factory lens calibration, portable fisheye/half-equirectangular conversion tools and AI-generated scene and visual-challenge annotations. Re-encoding the released fisheye and half-equirectangular renders with x265 over 24 clips, both eyes, four rate points and nine viewing directions, native-fisheye coding needed more bitrate than half-equirectangular coding at equal viewport quality for all 24 clips (median +38%), in every part of the field of view. Data: https://huggingface.co/datasets/lulinxuan/VR180 ; code: https://github.com/lulinxuan/vr180-dataset-tools", "url": "https://wpnews.pro/news/a-camera-native-stereo-vr180-dataset", "canonical_source": "https://arxiv.org/abs/2610.10607", "published_at": "2026-10-09 04:00:00+00:00", "updated_at": "2026-10-09 04:16:58.906783+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence"], "entities": ["Blackmagic URSA Cine Immersive", "Hugging Face", "GitHub", "x265", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/a-camera-native-stereo-vr180-dataset", "markdown": "https://wpnews.pro/news/a-camera-native-stereo-vr180-dataset.md", "text": "https://wpnews.pro/news/a-camera-native-stereo-vr180-dataset.txt", "jsonld": "https://wpnews.pro/news/a-camera-native-stereo-vr180-dataset.jsonld"}}