Local Ai
Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation
arXiv:2610.03439v1 Announce Type: new Abstract: Event cameras hold excellent dynamic properties, showing great potential for monocular depth estimation (MDE). However, existing methods mainly improve
arXiv:2610.03439v1 Announce Type: new Abstract: Event cameras hold excellent dynamic properties, showing great potential for monocular depth estimation (MDE). However, existing methods mainly improve performance by optimizing contextual features, but still struggle with the ill-posed and nonlinear nature of direct full-depth regression. In this paper, we propose HypoDepth, the first event-image monocular depth iterative refinement framework. By introducing a discrete Depth Hypothesis Volume (DHV), we transform the depth regression problem into a constrained depth search task. Specifically, we construct a 3D cost volume between the DHV features and contextual features and perform a multi-scale correlation search to guide stable residual optimization. This lightweight cost volume enables efficient global-to-local refinement across multi-resolution. Our method outperforms existing approaches on DSEC and MVSEC with state-of-the-art results and strong zero-shot generalization. Meanwhile, our tiny model achieves an excellent balance between accuracy and efficiency, enabling real-time performance on resource-limited devices.
Related
- E-S2Feat:Semantic-Guided Spiking Local Feature Detection and Description for Event Cameras
- MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
- CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention
- Efficient Hybrid CNN-GNN Architecture for Monocular Depth Estimation
Source: arXiv cs.CV | 2026-10-05