Papers › 6D-VNet: End-to-end 6DoF Vehicle Pose Estimation from Monocular RGB Images
6D-VNet: End-to-end 6DoF Vehicle Pose Estimation from Monocular RGB Images
Di Wu, Zhaoyong Zhuang, Canqun Xiang, Wenbin Zou and Xia Li
We present a conceptually simple framework for 6DoF object pose estimation, especially for autonomous driving scenario. Our approach efficiently detects traffic partic- ipants in a monocular RGB image while simultaneously regressing their 3D translation and rotation vectors. The method, called 6D-VNet, extends Mask R-CNN by adding customised heads for predicting vehicle s finer class, ro- tation and translation. The proposed 6D-VNet is trained end-to-end compared to previous methods. Furthermore, we show that the inclusion of translational regression in the joint losses is crucial for the 6DoF pose estimation task, where object translation distance along longitudinal axis varies significantly, e.g., in autonomous driving sce- narios. Additionally, we incorporate the mutual informa- tion between traffic participants via a modified non-local block. As opposed to the original non-local block imple- mentation, the proposed weighting modification takes the spatial neighbouring information into consideration whilst counteracting the effect of extreme gradient values. Our 6D-VNet reaches the 1 st place in ApolloScape challenge 3D Car Instance task1 [21]. Code has been made available at: https://github.com/stevenwudi/6DVNET.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections