Research map / 3D vision / Depth and stereo
Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an event-based differential focus volume prompting approach for dense metric depth estimation, addressing scale ambiguity and the low sampling rate of traditional depth-from-focus.
Problem
Dense metric depth estimation from single images suffers from scale ambiguity and visual illusions, while traditional depth-from-focus methods are limited by low sampling rates during data acquisition.
Approach
Uses event-camera data to build a differential focus volume that serves as a prompt for depth estimation, leveraging the high temporal resolution of events to overcome the low sampling rate of conventional focal stacks.
Closest papers by meaning
- Depth Prompting for Sensor-Agnostic Depth Estimation (CVPR 2024 · similarity 0.88)
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · similarity 0.87)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.87)
- Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation (CVPR 2025 · similarity 0.87)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.86)
- Active Event-based Stereo Vision (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.