Skip to content

liuem607/TLCFuse

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 

Repository files navigation

TLCFuse

We propose a novel approach for bird’s eye view semantic grid prediction that leverages sequential sensor data to achieve robustness against occlusions. Our model extracts information from the sensor readings using attention operations and aggregates this information into a lower-dimensional latent representation, enabling thus the processing of multi-step inputs at each prediction step. Additionally, we show how the model can be used with multimodal input sources and how it can also be directly applied to forecast the development of traffic scenes. We evaluate our model on the nuScenes dataset and show that it outperforms all competing multimodal methods on the vehicle segmentation task, with particularly large differences when evaluating on occluded and partially-occluded vehicles.

Architecture: Architecture

Qualitative results:

Predicting current time frame:

Scene A: Scene A

Scene B: Scene B

Predicting future frames:

cams prediction

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published