Research map / 3D vision / Depth and stereo
DepthInSpace: Exploitation and Fusion of Multiple Video Frames for Structured-Light Depth Estimation
Mohammad Mahdi Johari, Camilla Carta, François Fleuret
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 |
|---|---|---|---|
| fuse multiple video frames with optical flow (DIS-MF vs DIS-SF) | DIS-SF · Real dataset | outlier rate o(0.5): 17.95 -> 16.07 | Improved |
| fuse multiple video frames with optical flow (DIS-MF vs DIS-SF) | DIS-SF · Synthetic (Kinect pattern) | outlier rate o(1): 1.13 -> 0.72 | Improved |
| fine-tune single-frame network with fused depth as supervision (DIS-FTSF) | DIS-SF · Real dataset | outlier rate o(0.5): 17.95 -> 17.06 | Improved |
| fine-tune single-frame network with fused depth as supervision (DIS-FTSF) | DIS-SF · Synthetic (observed pattern) | outlier rate o(0.5): 3.66 -> 2.87 | Improved |
| add optical-flow guidance to self-supervised single-frame training (DIS-SF vs CTD) | CTD · Real dataset | outlier rate o(0.5): 22.74 -> 17.95 | Improved |
| add optical-flow guidance to self-supervised single-frame training (DIS-SF vs CTD) | CTD · Synthetic (Kinect pattern) | outlier rate o(0.5): 2.74 -> 2.11 | Improved |
| use denser Kinect dot pattern instead of observed pattern | DIS-MF · Synthetic | outlier rate o(0.5): 2.46 -> 1.59 | Improved |
| self-supervised DIS-SF vs supervised HyperDepth | HyperDepth · Real dataset | outlier rate o(0.5): 34.62 -> 17.95 | Improved |
| DIS-SF vs CTD at largest tolerance | CTD · Real dataset | outlier rate o(5): 1.00 -> 1.14 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- HyperDepth — HyperDepth: Learning Depth From Structured Light Without Matching (CVPR 2016) · better on 4 of 4 shared results
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
- Connecting the Dots: Learning Representations for Active Monocular Depth Estimation (CVPR 2019 · similarity 0.89)
- The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth (CVPR 2021 · similarity 0.89)
- HyperDepth: Learning Depth From Structured Light Without Matching (CVPR 2016 · similarity 0.89)
- Digging Into Self-Supervised Monocular Depth Estimation (ICCV 2019 · similarity 0.88)
- S³Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data (ECCV 2020 · similarity 0.88)
- Mind The Edge: Refining Depth Edges in Sparsely-Supervised Monocular Depth Estimation (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.
