Research map / 3D vision / Depth and stereo
AIMDepth: Asymmetric Image-Event Mamba for Monocular Depth Estimation
Luoxi Jing, Dianxi Shi, Yushe Cao, Yuanze Wang, Junze Zhang, Yuning Cui, Mengzhu Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add SCPG input-level spectral alignment (ablation) | AIMDepth baseline without modules · MVSEC (average) | Abs Rel: 0.539 -> 0.323 | Improved |
| add AME asymmetric encoder (ablation) | AIMDepth baseline without modules · MVSEC (average) | Abs Rel: 0.539 -> 0.300 | Improved |
| add ModiLocal alone (ablation) | AIMDepth baseline without modules · MVSEC (average) | Abs Rel: 0.539 -> 0.385 | Improved |
| add ModiLocal on top of AME and SCPG (ablation) | AME+SCPG · MVSEC (average) | Abs Rel: 0.351 -> 0.306 | Improved |
| add EAT to IPE in SCPG (ablation) | SCPG · MVSEC (average) | Abs Rel: 0.379 -> 0.323 | Improved |
| add IPE to EAT in SCPG (ablation) | SCPG · MVSEC (average) | Abs Rel: 0.428 -> 0.323 | Improved |
| add ISS to ModiLocal (ablation) | ModiLocal · MVSEC (average) | Abs Rel: 0.324 -> 0.306 | Improved |
| add LSS to ModiLocal (ablation) | ModiLocal · MVSEC (average) | Abs Rel: 0.309 -> 0.306 | Improved |
| AME alone in night scenes (ablation) | AIMDepth baseline · MVSEC Outdoor night1 | Abs Rel: 0.354 -> 0.331 | Mixed |
| use AIMDepth instead of fine-tuned Depth Anything V2 base | MVSEC day1/night1 average · MVSEC (average) | Abs Rel: 0.458 -> 0.306 | Improved |
| AIMDepth versus UniCT on MVSEC average abs rel | event-image fusion · MVSEC (average) | Abs Rel: 0.266 -> 0.306 | Hurt |
Closest papers by meaning
- Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation (CVPR 2026 · similarity 0.90)
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.87)
- DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain (NeurIPS 2024 · similarity 0.86)
- UniDepth: Universal Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.86)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.86)
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 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.
