16 citations · 42 across the 14 of their papers we have counts for
15 papers · 1 filter
Reprogramming Vision-Language Models via Structured Prompt Reparameterization
Zizhao Li, Chengyi Cai, Mohammed Yaqoob Ansari +3
Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In vision-language models, existi…
You Only Reprogram Once: Rethinking Prolonged Training for Visual Reprogramming
Zizhao Li, Mohammed Yaqoob Ansari, Xinyu Su +3
Visual reprogramming is a parameter-efficient method for adapting pretrained models, yet its training can remain computationally expensive: even with a frozen backbone, visual prom…
Relative Energy Learning for LiDAR Out-of-Distribution Detection
Zizhao Li, Zhengkang Xiang, Jiayang Ao +2
Out-of-distribution (OOD) detection is a critical requirement for reliable autonomous driving, where safety depends on recognizing road obstacles and unexpected objects beyond the…
rareboost3d: a synthetic lidar dataset with enhanced rare classes
Shutong Lin, Zhengkang Xiang, Jianzhong Qi +1
Real-world point cloud datasets have made significant contributions to the development of LiDAR-based perception technologies, such as object segmentation for autonomous driving. H…
Mapping Hidden Heritage: Self-supervised Pre-training on High-Resolution LiDAR DEM Derivatives for Archaeological Stone Wall Detection
Zexian Huang, Mashnoon Islam, Brian Armstrong +3
Historic dry-stone walls hold significant cultural and environmental importance, serving as historical markers and contributing to ecosystem preservation and wildfire management du…
Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion
Xueyang Kang, Zhengkang Xiang, Zezheng Zhang +1
Novel view synthesis (NVS) from a single image is highly ill-posed due to large unobserved regions, especially for views that deviate significantly from the input. While existing m…
Surfel-based 3D Registration with Equivariant SE(3) Features
Xueyang Kang, Hang Zhao, Kourosh Khoshelham +1
Point cloud registration is crucial for ensuring 3D alignment consistency of multiple local point clouds in 3D reconstruction for remote sensing or digital heritage. While various…
Out-of-distribution detection in 3D applications: a review
Zizhao Li, Xueyang Kang, Joseph West +1
The ability to detect objects that are not prevalent in the training set is a critical capability in many 3D applications, including autonomous driving. Machine learning methods fo…
SG-LDM: Semantic-Guided LiDAR Generation via Latent-Aligned Diffusion
Zhengkang Xiang, Zizhao Li, Amir Khodabandeh +1
Lidar point cloud synthesis based on generative models offers a promising solution to augment deep learning pipelines, particularly when real-world data is scarce or lacks diversit…
From Open Vocabulary to Open World: Teaching Vision Language Models to Detect Novel Objects
Zizhao Li, Zhengkang Xiang, Joseph West +1
Traditional object detection methods operate under the closed-set assumption, where models can only detect a fixed number of objects predefined in the training set. Recent works on…
Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration
Xueyang Kang, Zhaoliang Luan, Kourosh Khoshelham +1
Point cloud registration is a foundational task for 3D alignment and reconstruction applications. While both traditional and learning-based registration approaches have succeeded,…
Learning Geometric Invariant Features for Classification of Vector Polygons with Graph Message-passing Neural Network
Zexian Huang, Kourosh Khoshelham, Martin Tomko
Geometric shape classification of vector polygons remains a challenging task in spatial analysis. Previous studies have primarily focused on deep learning approaches for rasterized…
LMSeg: An end-to-end geometric message-passing network on barycentric dual graphs for large-scale landscape mesh segmentation
Zexian Huang, Kourosh Khoshelham, Martin Tomko
Semantic segmentation of large-scale 3D landscape meshes is critical for geospatial analysis in complex environments, yet existing approaches face persistent challenges of scalabil…
FocDepthFormer: Transformer with latent LSTM for Depth Estimation from Focal Stack
Xueyang Kang, Fengze Han, Abdur R. Fayjie +3
Most existing methods for depth estimation from a focal stack of images employ convolutional neural networks (CNNs) using 2D or 3D convolutions over a fixed set of images. However,…
Detecting Unsigned Physical Road Incidents from Driver-View Images
Alex Levering, Martin Tomko, Devis Tuia +1
Safety on roads is of uttermost importance, especially in the context of autonomous vehicles. A critical need is to detect and communicate disruptive incidents early and effectivel…