Research map / 3D vision / Depth and stereo
Hyper-Depth: Hypergraph-based Multi-Scale Representation Fusion for Monocular Depth Estimation
Lin Bie, Siqi Li, Yifan Feng, Yue Gao
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 SCE hypergraph module replacing PPM (ablation) | NewCRFs baseline · KITTI Eigen | RMSE: 2.129 -> 1.995 | Improved |
| add GCC module only (ablation) | NewCRFs baseline · KITTI Eigen | RMSE: 2.129 -> 2.062 | Improved |
| add C-CRFs module only (ablation) | NewCRFs baseline · KITTI Eigen | RMSE: 2.129 -> 2.103 | Improved |
| add GCC to SCE (ablation) | SCE · KITTI Eigen | RMSE: 1.995 -> 1.937 | Improved |
| add C-CRFs to SCE (ablation) | SCE · KITTI Eigen | RMSE: 1.995 -> 1.960 | Improved |
| add C-CRFs to SCE+GCC (ablation) | SCE+GCC · KITTI Eigen | RMSE: 1.937 -> 1.886 | Improved |
| add GCC to SCE+C-CRFs (ablation) | SCE+C-CRFs · KITTI Eigen | RMSE: 1.960 -> 1.886 | Improved |
| add C-CRFs only (ablation) | NewCRFs baseline · KITTI Eigen | Abs. Rel.: 0.053 -> 0.053 | No clear effect |
| add SCE hypergraph module replacing PPM (ablation) | NewCRFs baseline · KITTI Eigen | Abs. Rel.: 0.053 -> 0.049 | Improved |
| full Hyper-Depth versus NewCRFs (ablation) | NewCRFs · KITTI Eigen | RMSE: 2.129 -> 1.886 | Improved |
| Hyper-Depth versus ECoDepth (ablation) | ECoDepth · NYU-Depth-v2 | RMSE: 0.218 -> 0.211 | Improved |
| Hyper-Depth versus IEbins zero-shot (ablation) | IEbins · nuScenes zero-shot | RMSE: 3.028 -> 2.891 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- DCDepth — DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain (NeurIPS 2024) · better on 1 of 1 shared result
- DiffusionDepth — DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation (ECCV 2024) · better on 1 of 1 shared result
- NDDepth — NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion (TPAMI 2024) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation (CVPR 2024 · similarity 0.89)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.88)
- DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation (AAAI 2024 · similarity 0.88)
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (ICLR 2025 · similarity 0.88)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.87)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.87)
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.
