Research map / 3D vision / Depth and stereo
Boosting Monocular Depth Estimation With Lightweight 3D Point Fusion
Lam Huynh, Phong Nguyen, Jiří Matas, Esa Rahtu, Janne Heikkilä
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 confidence predictor (ablation) | Point-Fusion · NYU-Depth-v2 | RMSE: 0.097 -> 0.090 | Improved |
| add confidence predictor (ablation) | Point-Fusion · NYU-Depth-v2 | REL: 0.015 -> 0.014 | Improved |
| increase Fusion-Nets from 2 to 5 (ablation) | Point-Fusion · NYU-Depth-v2 | RMSE: 0.105 -> 0.090 | Improved |
| increase Fusion-Nets from 5 to 6 (ablation) | Point-Fusion · NYU-Depth-v2 | RMSE: 0.090 -> 0.093 | Hurt |
| add 3D point convolution branch (ablation) | Point-Fusion · NYU-Depth-v2 | RMSE: 0.196 -> 0.090 | Improved |
| use FKAConv instead of PCC (ablation) | Point-Fusion · NYU-Depth-v2 | RMSE: 0.096 -> 0.090 | Improved |
| use FKAConv instead of PCC (ablation) | Point-Fusion · NYU-Depth-v2 | #params: 9.1M -> 8.7M | Improved |
| sample input points from dense GT depth instead of COLMAP (ablation) | Point-Fusion · NYU-Depth-v2 | RMSE | Improved |
| add 32 sparse 3D points to the network | Point-Fusion · NYU-Depth-v2 | RMSE: 0.505 -> 0.319 | Improved |
| use Point-Fusion instead of NLSPN with 2 points | Point-Fusion vs NLSPN · NYU-Depth-v2 | RMSE: 1.152 -> 0.470 | Improved |
Closest papers by meaning
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.89)
- Flexible Depth Completion for Sparse and Varying Point Densities (CVPR 2024 · similarity 0.89)
- Distilling Monocular Foundation Model for Fine-grained Depth Completion (CVPR 2025 · similarity 0.88)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.88)
- Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation (CVPR 2024 · similarity 0.88)
- Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views (AAAI 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.
