A Camera-Native Stereo VR180 Dataset

Linxuan Lu

cs.CVOct 7, 2026

A Camera-Native Stereo VR180 Dataset

Authors: Linxuan Lu

Abstract

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

Explore similar work

SwiftVR: Real-Time One-Step Generative Video Restoration
Jun 8, 2026Jiaqi Yan, Xiangyu Chen, Xinlin Zhong +5Video Diffusion Models One-Step Generative Modeling
State Key Laboratory of Internet of Things for Smart City, Department of Computer and Information Science, University of Macau · Institute of Artificial Intelligence (TeleAI), China Telecom · State Key Laboratory for Novel Software Technology, Nanjing University
EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation
Sep 30, 2026Debabrata Mandal, Dongdong Fu, Jonathon Miller +3Video Diffusion Models
UNC Chapel Hill · Dolby Laboratories
StereoGenBench: A Synthetic Multi-Camera Benchmark for Stereo Generation under Controlled Baseline Regimes
May 22, 2026Yangzhi Cui, Feng Qiao, Nathan JacobsMulti-View Geometry Synthetic Benchmark Generation
Washington University in St. Louis

Jun 8, 2026, cs.CVJ/K move · Enter open · S save

SwiftVR: Real-Time One-Step Generative Video Restoration

Jiaqi Yan, Xiangyu Chen, Xinlin Zhong, Haibin Huang+4

State Key Laboratory of Internet of Things for Smart City, Department of Computer and Information Science, University of Macau · Institute of Artificial Intelligence (TeleAI), China Telecom · State Key Laboratory for Novel Software Technology, Nanjing University

Video Diffusion Models One-Step Generative Modeling Video Restoration Diffusion Model Inference Acceleration

Open paper AskPDF arXiv

Real-time video restoration (VR) for live streams requires high-resolution outputs under strict per-frame latency constraints. Existing one-step diffusion-based VR models remain difficult to deploy on consumer-grade GPUs due to two main bottlenecks: quadratic spatial attention at high resolutions and the latency-memory overhead of large video autoencoders. We present SwiftVR, a streaming one-step generative VR framework that reduces both bottlenecks under a causal chunk-wise protocol. For attention, mask-free shifted-window self-attention gathers each spatial window into a dense tensor via deterministic indexing, keeping all attention calls on the dense scaled dot-product attention path without masks, cyclic shifts, padding, or hardware-specific sparse kernels. Because SwiftVR uses only standard dense SDPA calls, the trained model transfers to consumer GPUs without retraining or custom kernels. For autoencoding, a lightweight Restoration-aware Autoencoder enables fast chunk-wise decoding while preserving reconstruction quality. On a single H100, SwiftVR sustains 31~~FPS at 2560x1440 and 14~~FPS at 3840x2160, whereas all compared diffusion-based VR baselines exceed the memory limit at 4K. On a consumer RTX~~5090, SwiftVR reaches 26~~FPS at 1920x1080. To our knowledge, SwiftVR is the first generative VR model to achieve real-time 1080p streaming on a consumer-grade GPU, while attaining strong no-reference perceptual quality with lower inference cost. Project is available at https://h-oliday.github.io/SwiftVR.

Abstract

Explore similar work

SwiftVR: Real-Time One-Step Generative Video Restoration

EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation

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