Robust Multimodal 3D Object Detection via Modality-Agnostic Decoding and Proximity-based Modality Ensemble

1 code implementation • 27 Jul 2024 • Juhan Cha, Minseok Joo, Jihwan Park, Sanghyeok Lee, Injae Kim, Hyunwoo J. Kim

Additionally, existing fusion methods overlook the detrimental impact of sensor noise induced by environmental changes, on detection performance.

3D Object Detection object-detection

Semantic-Aware Implicit Template Learning via Part Deformation Consistency

1 code implementation • ICCV 2023 • Sihyeon Kim, Minseok Joo, Jaewon Lee, Juyeon Ko, Juhan Cha, Hyunwoo J. Kim

In this paper, we highlight the importance of part deformation consistency and propose a semantic-aware implicit template learning framework to enable semantically plausible deformation.