Search Results for author:
Found 11 papers, 6 papers with code
VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene
We design a divide-and-conquer annotation scheme to solve the spatial extensibility problem of HD map generation, and abstract map elements with a variety of geometric patterns as unified point sequence representation, which can be extended to most map elements in the driving scene.
RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representation
This paper introduces RoMe, a novel framework designed for the robust reconstruction of large-scale road surfaces.
A Vision-Centric Approach for Static Map Element Annotation
The recent development of online static map element (a. k. a.
Towards Accurate Ground Plane Normal Estimation from Ego-Motion
In this paper, we introduce a novel approach for ground plane normal estimation of wheeled vehicles.
VRSO: Visual-Centric Reconstruction for Static Object Annotation
As a part of the perception results of intelligent driving systems, static object detection (SOD) in 3D space provides crucial cues for driving environment understanding.
Gyroscope-Assisted Motion Deblurring Network
Yet, their practical usage in real-world deblurring, especially motion blur, remains limited due to the lack of pixel-aligned training triplets (background, blurred image, and blur heat map) and restricted information inherent in blurred images.
Do We Need Binary Features for 3D Reconstruction?
Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors.
Deep Online Correction for Monocular Visual Odometry
Second, the poses predicted by CNNs are further improved by minimizing photometric errors via gradient updates of poses during inference phases.
Monocular Road Planar Parallax Estimation
It implies planar parallax and can be combined with the road plane serving as a reference to estimate the 3D structure by warping the consecutive frames.
Road-aware Monocular Structure from Motion and Homography Estimation
The Depth-CNN and Pose-CNN estimate dense depth map and ego-motion respectively, solving SFM, while the Pose-CNN and Ground-CNN followed by a homography layer solve the ground plane estimation problem.
BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation
Moreover, we find that the image feature maps' resolution in the cross-attention module has a limited effect on the final performance.
Ranked #6 on
Bird's-Eye View Semantic Segmentation
on nuScenes
