GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction
GeoRoute:面向交通未来帧预测的几何感知混合推理方法
Khang Minh Le, Hieu Dinh Trung Pham, Luu Thanh Danh, Nam-Tien Le, Hieu Anh Ngo, Phuong Huu Vu Tran, Son Nguyen Minh Le, Nguyen Trong Nghia, Tu Tran Thi Cam, Huy Minh Nhat Nguyen, Cuong Tuan Nguyen
机构
*
Vietnamese-German University(越南-德国大学)
;
University of Science, Ho Chi Minh City(胡志明市科学大学)
;
Ho Chi Minh City University of Technology(胡志明市技术大学)
;
University of Information Technology, Ho Chi Minh City(胡志明市信息技术大学)
专题命中
感知
:autonomous driving(abstract);分类 cs.CV
AI总结
GeoRoute是一种无需训练的几何感知混合推理框架,通过多帧深度分层渲染器和视角条件选择预测器,在AI City Challenge Track 5基准上实现了具有竞争力的交通未来帧预测性能,提升了静态几何稳定性。
Commentsaccepted to the ECCV 2026 AI City Challenge Workshop
Comments23 pages, 5 figures, 4 tables. Includes a correctness result for TSDF fusion implementations: at hash load factors reached by ordinary depth trajectories, the Triton implementation silently discards blocks. Code, raw measurement CSVs and an interactive viewer: https://github.com/realitymatrix/what-irregularity-costs