From 9fdd5892e96c1abde4eae1b1659170c69d69945d Mon Sep 17 00:00:00 2001 From: mwlasiuk Date: Sun, 16 Aug 2026 13:27:28 +0200 Subject: [PATCH] Add AI_LIO_+ --- bib/AI_LIO_PLUS_Survey.bib | 13 +++++++++++++ documentation/Benchmarks/AI_LIO+/README.md | 3 +++ 2 files changed, 16 insertions(+) create mode 100644 bib/AI_LIO_PLUS_Survey.bib create mode 100644 documentation/Benchmarks/AI_LIO+/README.md diff --git a/bib/AI_LIO_PLUS_Survey.bib b/bib/AI_LIO_PLUS_Survey.bib new file mode 100644 index 00000000..8114767f --- /dev/null +++ b/bib/AI_LIO_PLUS_Survey.bib @@ -0,0 +1,13 @@ +@article{TAO2026134317, +title = {Generalized deep-learning LiDAR-camera fusion method of 3D object detection for autonomous driving: A survey}, +journal = {Neurocomputing}, +volume = {699}, +pages = {134317}, +year = {2026}, +issn = {0925-2312}, +doi = {https://doi.org/10.1016/j.neucom.2026.134317}, +url = {https://www.sciencedirect.com/science/article/pii/S0925231226017157}, +author = {Xianlu Tao and Zhuo Chen and Shuguo Pan and Wang Gao and Gaoyang Xiong and Feixuan Huang}, +keywords = {3D object detection, Deep learning, Multimodal, LiDAR, Camera, Autonomous driving}, +abstract = {With the rapid advancement of deep learning and increasing demands from autonomous driving, LiDAR–camera fusion-based 3D object detection (3DOD) has become a fundamental real-time perception task. The core challenge of such multimodal systems lies in mitigating modality discrepancies and effectively modeling cross-modal feature correlations. This paper presents a survey on LiDAR-camera fusion 3DOD in autonomous driving scenarios, with a focus on open-source autonomous driving datasets containing LiDAR-camera data in the real world, as well as the classification and development of LiDAR-camera fusion methods. Unlike prior surveys that focus on overall network architectures, we emphasize the implementation details of fusion strategies to enable a more thorough comparison. We further summarize a novel generalized fusion taxonomy, termed Representation-Augmented Fusion and Representation-Unified Fusion (RAF-RUF), to better reflect current research trends. In addition, fusion approaches involving other camera types and cooperative perception scenarios are briefly reviewed. Finally, open datasets and future research directions are discussed to facilitate practical deployment and further studies.} +} \ No newline at end of file diff --git a/documentation/Benchmarks/AI_LIO+/README.md b/documentation/Benchmarks/AI_LIO+/README.md new file mode 100644 index 00000000..6e773a39 --- /dev/null +++ b/documentation/Benchmarks/AI_LIO+/README.md @@ -0,0 +1,3 @@ +# AI_LIO+ (no assignee) + +- https://www.sciencedirect.com/science/article/pii/S0925231226017157?via%3Dihub ([[BIB]](https://github.com/MapsHD/HDMapping/blob/main/bib/AI_LIO_PLUS_Survey.bib), no source code - survey article containing links to methods)