Paper ID | IVMSP-22.3 | ||
Paper Title | HIERARCHICAL CONTEXT GUIDED AGGREGATION NETWORK FOR STEREO MATCHING | ||
Authors | Jun Peng, Wangduo Xie, Zijing Huang, Wei Chen, Yong Zhao, Shenzhen Graduate School of Peking University, China | ||
Session | IVMSP-22: Image & Video Sensing, Modeling and Representation | ||
Location | Gather.Town | ||
Session Time: | Thursday, 10 June, 14:00 - 14:45 | ||
Presentation Time: | Thursday, 10 June, 14:00 - 14:45 | ||
Presentation | Poster | ||
Topic | Image, Video, and Multidimensional Signal Processing: [IVARS] Image & Video Analysis, Synthesis, and Retrieval | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Nowadays, CNN-based stereo matching methods achieved remarkable performance, and how to efficiently exploit contextual information in cost aggregation stage is the key to improve performance. In this paper, we propose a simple yet efficient network named Hierarchical Context Guided Aggregation Network (HCGANet). Specifically, a novel cost aggregation module is developed to replace widely used 3D convolutions. Firstly, we construct pyramid cost volumes which carry multi-level distinctive and discriminative representation. Additionally, an intra-level aggregation module is presented for single-level regularization and contextual information learning. Moreover, we develop an inter-level aggregation module to hierarchically regularize cost volumes via the guidance from coarser scales. The proposed aggregation module is lightweight and complementary, further improving the robustness and performance of disparity estimation. Extensive experiments demonstrate that the proposed method achieves superior results for both efficiency and accuracy on SceneFlow and KITTI benchmarks. |