Summary of Improving Robustness Of Lidar-camera Fusion Model Against Weather Corruption From Fusion Strategy Perspective, by Yihao Huang et al.
Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
by Yihao Huang, Kaiyuan Yu, Qing Guo, Felix Juefei-Xu, Xiaojun Jia, Tianlin Li, Geguang Pu, Yang Liu
First submitted to arxiv on: 5 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper investigates the robustness of LiDAR-camera fusion models for 3D object detection in autonomous driving under various weather conditions. Recent advances have improved performance, but their resilience to fog, rain, snow, and sunlight is understudied. The authors evaluate different fusion strategies on a corrupted dataset, finding that their proposed flexibly weighted fusing approach enhances robustness by adaptively combining LiDAR and camera features across weather scenarios. This method is tested on four types of fusion models with two lightweight implementations, demonstrating its effectiveness. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how well computer vision models can detect objects in self-driving cars when the weather is bad. Right now, these models work pretty well, but they need to get better at handling things like fog, rain, and snow. The researchers tested different ways of combining data from LiDAR sensors and cameras to see which one works best. They found that a simple method that adjusts how much weight each source gets based on the weather works really well. |
Keywords
* Artificial intelligence * Object detection
