Active Stereo Without Pattern Projector
Luca Bartolomei, Matteo Poggi, Fabio Tosi, Andrea Conti, Stefano Mattoccia
Abstract
This paper proposes a novel framework integrating the principles of active stereo in standard passive camera systems without a physical pattern projector. We virtually project a pattern over the left and right images according to the sparse measurements obtained from a depth sensor. Any such devices can be seamlessly plugged into our framework, allowing for the deployment of a virtual active stereo setup in any possible environment, overcoming the limitation of pattern projectors, such as limited working range or environmental conditions. Experiments on indoor/outdoor datasets, featuring both long and close-range, support the seamless effectiveness of our approach, boosting the accuracy of both stereo algorithms and deep networks.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 749c5637-c179-4399-b6c5-3537dede4ef5Cited by top-tier papers3
- Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono FailLuca Bartolomei, Fabio Tosi, Matteo Poggi, Stefano MattocciaCVPR 2025
- GS-ASM: 2DGS-Supervised Active Stereo MatchingZhengling Wu, Rongfeng Lu, Quan Chen, Longjian Zeng et al.CVPR 2026
- Active Event-based Stereo VisionJianing Li, Yunjian Zhang, Haiqian Han, Xiangyang JiCVPR 2025
Builds on15
- Hierarchical Neural Architecture Search for Deep Stereo MatchingXuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai et al.NeurIPS 2020 · 436 citations
- Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with TransformersZhaoshuo Li, Xingtong Liu, Nathan Drenkow, Andy S. Ding et al.ICCV 2021 · 380 citations
- Practical Stereo Matching via Cascaded Recurrent Network with Adaptive CorrelationJiankun Li, Peisen Wang, Pengfei Xiong, Tao Cai et al.CVPR 2022 · 294 citations
- Learning Joint 2D-3D Representations for Depth CompletionYun Chen, Bin Yang, Ming Liang, Raquel UrtasunICCV 2019 · 190 citations
- Dynamic Spatial Propagation Network for Depth CompletionYuankai Lin, Tao Cheng, Qi Zhong, Wending Zhou et al.AAAI 2022 · 155 citations
Related papers
- Depth Estimation by Combining Binocular Stereo and Monocular Structured-LightYuhua Xu, Xiaoli Yang, Yushan Yu, Wei Jia et al.CVPR 2022 · 12 citations
- ActiveZero: Mixed Domain Learning for Active Stereovision with Zero AnnotationIsabella Liu, Edward Yang, Jianyu Tao, Rui Chen et al.CVPR 2022
- Sensor-Guided Optical FlowMatteo Poggi, Filippo Aleotti, Stefano MattocciaICCV 2021 · 5 citations
- Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous DrivingYurong You, Yan Wang, Wei-Lun Chao, Divyansh Garg et al.ICLR 2020 · 439 citations
- CodedStereo: Learned Phase Masks for Large Depth-of-Field StereoShiyu Tan, Yicheng Wu, Shoou-I Yu, Ashok VeeraraghavanCVPR 2021
