6 papers
The Midas Touch for Metric Depth: Interpretable Metricization for Generalizable Depth Perception
Mengtan Zhang, Yu Ma, Shiqi Jiang +6
Recent foundation models have drastically improved the generalization of monocular relative depth estimation, yet recovering accurate metric depth from their estimates for depth pe…
KVE-KD: Key Visual Evidence-Guided Knowledge Distillation for Vision-Language Models
Jianbin Zhang, Xin Sun, Shanwen Wang +2
Knowledge distillation is crucial for deploying vision-language models on resource-constrained devices. However, existing methods typically impose uniform supervision across visual…
Binaural Audio-Visual Instance Segmentation
Saijun Wang, Guanfeng Tang, Hongbo Zhao +4
Audio-visual segmentation (AVS) aims to segment sounding objects at the pixel level by integrating auditory and visual cues. However, existing methods are predominantly developed u…
DiCycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schrödinger Bridge Transformer
Hanting Li, Xin Sun, Wei Ye +2
Light-effect contamination poses a significant challenge to nighttime visibility enhancement. Most methods suppress light effects by estimating and decomposing them through prior-d…
Two-Stream Interactive Joint Learning of Scene Parsing and Geometric Vision Tasks
Guanfeng Tang, Hongbo Zhao, Ziwei Long +5
Inspired by the human visual system, which operates on two parallel yet interactive streams for contextual and spatial understanding, this article presents Two Interactive Streams…
Rebenchmarking Unsupervised Monocular 3D Occupancy Prediction
Zizhan Guo, Yi Feng, Mengtan Zhang +3
Inferring the 3D structure from a single image, particularly in occluded regions, remains a fundamental yet unsolved challenge in vision-centric autonomous driving. Existing unsupe…