ThermalLoc combines EfficientNet and a Vision Transformer to regress 6-DoF camera poses from single thermal images, reporting improved relocalization accuracy on city-scale thermal datasets.
EffLoc: Lightweight Vision Transformer for Efficient 6-DOF Camera Relocalization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Camera relocalization is pivotal in computer vision, with applications in AR, drones, robotics, and autonomous driving. It estimates 3D camera position and orientation (6-DoF) from images. Unlike traditional methods like SLAM, recent strides use deep learning for direct end-to-end pose estimation. We propose EffLoc, a novel efficient Vision Transformer for single-image camera relocalization. EffLoc's hierarchical layout, memory-bound self-attention, and feed-forward layers boost memory efficiency and inter-channel communication. Our introduced sequential group attention (SGA) module enhances computational efficiency by diversifying input features, reducing redundancy, and expanding model capacity. EffLoc excels in efficiency and accuracy, outperforming prior methods, such as AtLoc and MapNet. It thrives on large-scale outdoor car-driving scenario, ensuring simplicity, end-to-end trainability, and eliminating handcrafted loss functions.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ThermalLoc: A Vision Transformer-Based Approach for Robust Thermal Camera Relocalization in Large-Scale Environments
ThermalLoc combines EfficientNet and a Vision Transformer to regress 6-DoF camera poses from single thermal images, reporting improved relocalization accuracy on city-scale thermal datasets.