activity
20172022
most citedA Robust Laser-Inertial Odometry and Mapping Method for Large-Scale Highway Environments

97 citations · 306 across the 41 of their papers we have counts for

collaborators
Showing cs.CVShow all

21 papers · 1 filter

cs.CV20228 cited

Pseudo-Label Noise Suppression Techniques for Semi-Supervised Semantic Segmentation

Sebastian Scherer, Robin Schön, Rainer Lienhart

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic seg…

cs.CV20224 cited

TartanCalib: Iterative Wide-Angle Lens Calibration using Adaptive SubPixel Refinement of AprilTags

Bardienus P Duisterhof, Yaoyu Hu, Si Heng Teng +2

Wide-angle cameras are uniquely positioned for mobile robots, by virtue of the rich information they provide in a small, light, and cost-effective form factor. An accurate calibrat…

cs.CV20221 cited

360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidance

Shreyas Kulkarni, Peng Yin, Sebastian Scherer

We present a method to synthesize novel views from a single panorama image based on the neural radiance field (NeRF). Prior studies in a similar setting rely on the nei…

cs.CV20221 cited

iSimLoc: Visual Global Localization for Previously Unseen Environments with Simulated Images

Peng Yin, Ivan Cisneros, Ji Zhang +2

The visual camera is an attractive device in beyond visual line of sight (B-VLOS) drone operation, since they are low in size, weight, power, and cost, and can provide redundant mo…

cs.CV202189 cited

3D-SiamRPN: An End-to-End Learning Method for Real-Time 3D Single Object Tracking Using Raw Point Cloud

Zheng Fang, Sifan Zhou, Yubo Cui +1

3D single object tracking is a key issue for autonomous following robot, where the robot should robustly track and accurately localize the target for efficient following. In this p…

cs.CV2021

3D Segmentation Learning from Sparse Annotations and Hierarchical Descriptors

Peng Yin, Lingyun Xu, Jianmin Ji +2

One of the main obstacles to 3D semantic segmentation is the significant amount of endeavor required to generate expensive point-wise annotations for fully supervised training. To…