CFSR reframes shadow removal as a physics-constrained process using geometric and semantic priors from depth, DINO, CLIP, and frequency decoupling to achieve claimed state-of-the-art results.
Depth anything v2
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DPG-CD uses an estimated depth prior from imagery, gated fusion, and multi-stage cross-modal architecture to jointly predict 2D semantic and 3D height changes, outperforming prior methods on Hi-BCD, 3DCD, and NYC-MMCD datasets.
A depth completion network trained on synthetic field-robotics scenes predicts dense metric depth from extremely sparse real measurements and runs in real time on embedded hardware in unseen outdoor environments.
citing papers explorer
-
CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement
CFSR reframes shadow removal as a physics-constrained process using geometric and semantic priors from depth, DINO, CLIP, and frequency decoupling to achieve claimed state-of-the-art results.
-
DPG-CD: Depth-Prior-Guided Cross-Modal Joint 2D-3D Change Detection
DPG-CD uses an estimated depth prior from imagery, gated fusion, and multi-stage cross-modal architecture to jointly predict 2D semantic and 3D height changes, outperforming prior methods on Hi-BCD, 3DCD, and NYC-MMCD datasets.
-
Depth Completion in Unseen Field Robotics Environments Using Extremely Sparse Depth Measurements
A depth completion network trained on synthetic field-robotics scenes predicts dense metric depth from extremely sparse real measurements and runs in real time on embedded hardware in unseen outdoor environments.