3 papers
cs.CV2026
Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization
Yumiao Zhao, Bo Jiang, Beibei Wang +3
Visual Prompting (VP) has emerged as an efficient paradigm for adapting large-scale pre-trained vision models to downstream tasks by incorporating learnable prompts at the input le…
cs.CV2026
Language as Prior, Vision as Calibration: Metric Scale Recovery for Monocular Depth Estimation
Mingxia Zhan, Li Zhang, Beibei Wang +2
Relative-depth foundation models transfer well, yet monocular metric depth remains ill-posed due to unidentifiable global scale and heightened domain-shift sensitivity. Under a fro…
cs.CV2025
VistaDepth: Improving far-range Depth Estimation with Spectral Modulation and Adaptive Reweighting
Mingxia Zhan, Li Zhang, Yingjie Wang +3
Monocular depth estimation (MDE) aims to infer per-pixel depth from a single RGB image. While diffusion models have advanced MDE with impressive generalization, they often exhibit…