- Keywords: Self-driving, distance estimation, long-range objects
- Abstract: Estimating the distance of objects is a safety-critical task for autonomous driving. Focusing on the short-range objects, existing methods and datasets neglect the equally important long-range objects. In this paper, we name this challenging but underexplored task as Long-Range Distance Estimation, and propose two datasets for this task. We then propose R4D, the first framework to accurately estimate the distance of long-range objects by using references with known distances in the scene. Drawing inspiration from human perception, R4D builds a graph by connecting a target object to all references. An edge in the graph encodes the relative distance information between a pair of target and reference objects. An attention module is then used to weigh the importance of reference objects and combine them into one target object distance prediction. Experiments on the two proposed datasets demonstrate the effectiveness and robustness of R4D by showing significant improvements compared to existing baselines.
- Supplementary Material: zip