BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yijin, Shen, Yichen, Huang, Zhaoyang, Chen, Shuo, Bian, Weikang, Shi, Xiaoyu, Wang, Fu-Yun, Sun, Keqiang, Bao, Hujun, Cui, Zhaopeng, Zhang, Guofeng, Li, Hongsheng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913684389888000
author Li, Yijin
Shen, Yichen
Huang, Zhaoyang
Chen, Shuo
Bian, Weikang
Shi, Xiaoyu
Wang, Fu-Yun
Sun, Keqiang
Bao, Hujun
Cui, Zhaopeng
Zhang, Guofeng
Li, Hongsheng
author_facet Li, Yijin
Shen, Yichen
Huang, Zhaoyang
Chen, Shuo
Bian, Weikang
Shi, Xiaoyu
Wang, Fu-Yun
Sun, Keqiang
Bao, Hujun
Cui, Zhaopeng
Zhang, Guofeng
Li, Hongsheng
contents Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynamic range, making them well-suited for correspondence tasks such as optical flow and point tracking. However, there is still a lack of comprehensive benchmarks for correspondence tasks that include both event data and images. To address this gap, we propose BlinkVision, a large-scale and diverse benchmark with multiple modalities and dense correspondence annotations. BlinkVision offers several valuable features: 1) Rich modalities: It includes both event data and RGB images. 2) Extensive annotations: It provides dense per-pixel annotations covering optical flow, scene flow, and point tracking. 3) Large vocabulary: It contains 410 everyday categories, sharing common classes with popular 2D and 3D datasets like LVIS and ShapeNet. 4) Naturalistic: It delivers photorealistic data and covers various naturalistic factors, such as camera shake and deformation. BlinkVision enables extensive benchmarks on three types of correspondence tasks (optical flow, point tracking, and scene flow estimation) for both image-based and event-based methods, offering new observations, practices, and insights for future research. The benchmark website is https://www.blinkvision.net/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20451
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events
Li, Yijin
Shen, Yichen
Huang, Zhaoyang
Chen, Shuo
Bian, Weikang
Shi, Xiaoyu
Wang, Fu-Yun
Sun, Keqiang
Bao, Hujun
Cui, Zhaopeng
Zhang, Guofeng
Li, Hongsheng
Computer Vision and Pattern Recognition
Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynamic range, making them well-suited for correspondence tasks such as optical flow and point tracking. However, there is still a lack of comprehensive benchmarks for correspondence tasks that include both event data and images. To address this gap, we propose BlinkVision, a large-scale and diverse benchmark with multiple modalities and dense correspondence annotations. BlinkVision offers several valuable features: 1) Rich modalities: It includes both event data and RGB images. 2) Extensive annotations: It provides dense per-pixel annotations covering optical flow, scene flow, and point tracking. 3) Large vocabulary: It contains 410 everyday categories, sharing common classes with popular 2D and 3D datasets like LVIS and ShapeNet. 4) Naturalistic: It delivers photorealistic data and covers various naturalistic factors, such as camera shake and deformation. BlinkVision enables extensive benchmarks on three types of correspondence tasks (optical flow, point tracking, and scene flow estimation) for both image-based and event-based methods, offering new observations, practices, and insights for future research. The benchmark website is https://www.blinkvision.net/.
title BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.20451