Research map / 3D vision / Depth and stereo
GEDepth: Ground Embedding for Monocular Depth Estimation
Xiaodong Yang, Zhuang Ma, Zhiyu Ji, Zhe Ren
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 |
|---|---|---|---|
| plug GEDepth-Adaptive into DepthFormer, PixelFormer, BinsFormer, BTS | depth networks · KITTI | Abs Rel: 0.052 -> 0.048 (DepthFormer) | Improved |
| use GEDepth-Adaptive instead of Vanilla (model slope) (ablation) | GEDepth · KITTI sloping-scene subset | Abs Rel: 0.064 -> 0.057 | Improved |
| add GEDepth-Vanilla to PixelFormer on KITTI (ablation) | PixelFormer · KITTI | RMSE: 2.081 -> 2.071 | No clear effect |
| add ground embedding for cross-dataset transfer KITTI to DDAD | DepthFormer · KITTI to DDAD | Abs Rel: 0.644 -> 0.261 | Improved |
| add ground embedding for cross-dataset transfer DDAD to KITTI | DepthFormer · DDAD to KITTI | Abs Rel: 0.149 -> 0.104 | Improved |
| add ground embedding, evaluate ground vs non-ground (ablation) | DepthFormer · KITTI | Abs Rel: ground 0.032 -> 0.028; non-ground 0.078 -> 0.074 | Improved |
| embed ground depth in the input instead of the encoder (ablation) | GEDepth-Adaptive · KITTI | Abs Rel: 0.049 -> 0.048 | Improved |
| vary ground slope range and binning (ablation) | GEDepth-Adaptive · KITTI | Abs Rel: 0.048 to 0.049 | No clear effect |
| vary classification loss weight lambda_cls (ablation) | GEDepth-Adaptive · KITTI | Abs Rel: 0.049 -> 0.048 at 0.10 | No clear effect |
| add GEDepth to DepthFormer for compute | DepthFormer · KITTI | inference latency: 179ms -> 185ms | Hurt |
Closest papers by meaning
- GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation (CVPR 2025 · similarity 0.88)
- From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior (CVPR 2024 · similarity 0.87)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.87)
- DME: Unveiling the Bias for Better Generalized Monocular Depth Estimation (AAAI 2024 · similarity 0.87)
- ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation (CVPR 2024 · similarity 0.86)
- DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain (NeurIPS 2024 · 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.
