activity
20162024
most citedLAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints

6 citations · 13 across the 14 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2024

Learning from Exemplars for Interactive Image Segmentation

Kun Li, Hao Cheng, George Vosselman +1

Interactive image segmentation enables users to interact minimally with a machine, facilitating the gradual refinement of the segmentation mask for a target of interest. Previous s…

cs.CV2024

Robust Shape Fitting for 3D Scene Abstraction

Florian Kluger, Eric Brachmann, Michael Ying Yang +1

Humans perceive and construct the world as an arrangement of simple parametric models. In particular, we can often describe man-made environments using volumetric primitives such a…

cs.CV20231 cited

BuilDiff: 3D Building Shape Generation using Single-Image Conditional Point Cloud Diffusion Models

Yao Wei, George Vosselman, Michael Ying Yang

3D building generation with low data acquisition costs, such as single image-to-3D, becomes increasingly important. However, most of the existing single image-to-3D building creati…

cs.CV20236 cited

LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints

Mengmeng Liu, Hao Cheng, Lin Chen +5

Trajectory prediction for autonomous driving must continuously reason the motion stochasticity of road agents and comply with scene constraints. Existing methods typically rely on…

cs.CV2023

HRVQA: A Visual Question Answering Benchmark for High-Resolution Aerial Images

Kun Li, George Vosselman, Michael Ying Yang

Visual question answering (VQA) is an important and challenging multimodal task in computer vision. Recently, a few efforts have been made to bring VQA task to aerial images, due t…

cs.CV20165 cited

Can Ground Truth Label Propagation from Video help Semantic Segmentation?

Siva Karthik Mustikovela, Michael Ying Yang, Carsten Rother

For state-of-the-art semantic segmentation task, training convolutional neural networks (CNNs) requires dense pixelwise ground truth (GT) labeling, which is expensive and involves…