Key-point-based scene understanding is fundamental for autonomous driving applications. At the same time, optical flow plays an important role in many vision tasks. However, due to the implicit bias of equal attention on all points, classic data-driven optical flow estimation methods yield less satisfactory performance on key points, limiting their implementations in key-point-critical safety-relevant scenarios. To address these issues, we introduce a points-based modeling method that requires the model to learn key-point-related priors explicitly. Based on the modeling method, we present FocusFlow, a framework consisting of 1) a mix loss function combined with a classic photometric loss function and our proposed Conditional Point Control Loss (CPCL) function for diverse point-wise supervision; 2) a conditioned controlling model which substitutes the conventional feature encoder by our proposed Condition Control Encoder (CCE). CCE incorporates a Frame Feature Encoder (FFE) that extracts features from frames, a Condition Feature Encoder (CFE) that learns to control the feature extraction behavior of FFE from input masks containing information of key points, and fusion modules that transfer the controlling information between FFE and CFE. Our FocusFlow framework shows outstanding performance with up to ${+}44.5\%$ precision improvement on various key points such as ORB, SIFT, and even learning-based SiLK, along with exceptional scalability for most existing data-driven optical flow methods like PWC-Net, RAFT, and FlowFormer. Notably, FocusFlow yields competitive or superior performances rivaling the original models on the whole frame.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    FocusFlow: Boosting Key-Points Optical Flow Estimation for Autonomous Driving


    Contributors:
    Yi, Zhonghua (author) / Shi, Hao (author) / Yang, Kailun (author) / Jiang, Qi (author) / Ye, Yaozu (author) / Wang, Ze (author) / Ni, Huajian (author) / Wang, Kaiwei (author)

    Published in:

    Publication date :

    2024-01-01


    Size :

    4569380 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Determining driving paths for autonomous driving vehicles based on offset points

    ZHANG LIANGLIANG / DONG LI / ZHU FAN et al. | European Patent Office | 2021

    Free access

    Optical Flow based Visual Potential Field for Autonomous Driving

    Capito, Linda / Ozguner, Umit / Redmill, Keith | IEEE | 2020


    RISK ESTIMATION IN AUTONOMOUS DRIVING ENVIRONMENTS

    GYLLENHAMMAR MAGNUS / SIVENCRONA HÅKAN | European Patent Office | 2022

    Free access

    WHEEL TORQUE ESTIMATION FOR AUTONOMOUS DRIVING

    LIU JINGXUAN / KURT ARDA / JING JUNBO | European Patent Office | 2023

    Free access

    RISK ESTIMATION IN AUTONOMOUS DRIVING ENVIRONMENTS

    GYLLENHAMMAR MAGNUS / SIVENCRONA HÅKAN | European Patent Office | 2022

    Free access