Research map / 3D vision / Depth and stereo
Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation
Daikun Liu, Teng Wang, Changyin Sun
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 EIFusion (cross-attention/conv fusion) instead of concatenation (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.110 -> 0.105 | Improved |
| add cross-attention between DHV embeddings and context in decoder (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.111 -> 0.105 | Improved |
| add GRU unit instead of convolution layers (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.115 -> 0.105 | Improved |
| add contextual features in the decoder (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.112 -> 0.105 | Improved |
| add multi-scale pooling in correlation lookup (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.110 -> 0.105 | Improved |
| add discrete Depth Hypothesis Volume instead of continuous previous depth (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.113 -> 0.105 | Improved |
| increase iterations per stage from 2 to 8 (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.117 -> 0.105 | Improved |
| increase iterations per stage from 8 to 12 (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.105 -> 0.117 | Hurt |
| increase lookup radius from 0 to 8 (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.116 -> 0.105 | Improved |
| increase D across resolutions from 32, 32, 32 to 32, 64, 96 (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.114 -> 0.105 | Improved |
| add finer resolutions 1/8 and 1/4 to refinement (from 1/16 only) (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.126 -> 0.105 | Improved |
| lengthen event slice from 20 ms to 50 ms (ablation) | HypoDepth · DSEC (scaled-down model) | Abs Rel: 0.105 -> 0.106 | No clear effect |
Closest papers by meaning
- Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation (ICCV 2025 · similarity 0.90)
- DERD-Net: Learning Depth from Event-based Ray Densities (NeurIPS 2025 · similarity 0.88)
- BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation (NeurIPS 2024 · similarity 0.87)
- Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain (NeurIPS 2024 · similarity 0.86)
- Event-Driven Dynamic Scene Depth Completion (NeurIPS 2025 · similarity 0.86)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · 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.
