4 papers
ColorFD: A Finite-Difference Guided Black-Box Physical Adversarial Attack for Remote Sensing Object Detection
Tiannuo Guo, Guhang Qiu, Yuzhen Xie +3
Although deep neural network-based remote sensing object detectors have achieved strong performance, they remain vulnerable to adversarial perturbations. Existing studies mainly fo…
Blind Quality Enhancement for G-PCC Compressed Dynamic Point Clouds
Tian Guo, Hui Yuan, Chang Sun +3
Point cloud compression often introduces noticeable reconstruction artifacts, which makes quality enhancement necessary. Existing approaches typically assume prior knowledge of the…
AR as an Evaluation Playground: Bridging Metrics and Visual Perception of Computer Vision Models
Ashkan Ganj, Yiqin Zhao, Tian Guo
Quantitative metrics are central to evaluating computer vision (CV) models, but they often fail to capture real-world performance due to protocol inconsistencies and ground-truth n…
HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors
Ashkan Ganj, Hang Su, Tian Guo
We propose HYBRIDDEPTH, a robust depth estimation pipeline that addresses key challenges in depth estimation,including scale ambiguity, hardware heterogeneity, and generalizability…