ViM-Disparity: Bridging the Gap of Speed, Accuracy and Memory for Disparity Map Generation
This work addresses the problem of efficient and accurate disparity estimation for applications like robotics or autonomous driving, representing an incremental improvement in model design.
The authors tackled the trade-off between speed, accuracy, and memory in disparity map generation by proposing a Visual Mamba-based architecture, achieving real-time performance with low computational overhead.
In this work we propose a Visual Mamba (ViM) based architecture, to dissolve the existing trade-off for real-time and accurate model with low computation overhead for disparity map generation (DMG). Moreover, we proposed a performance measure that can jointly evaluate the inference speed, computation overhead and the accurateness of a DMG model. The code implementation and corresponding models are available at: https://github.com/MBora/ViM-Disparity.