Research map / 3D vision / Depth and stereo
PRISM-VO: Scale-Aware Visual Odometry Using Photometric Plenoptic Bundle Adjustment
Aymeric Fleith, Julian Zirbel, Daniel Cremers, Niclas Zeller
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 plenoptic depth initialization and explicit plenoptic projection to a pinhole baseline (ablation) | PRISM-VO · drift study ablation | scale drift / absolute scale | Improved |
| add variance-weighted inverse virtual depth residual with adaptive balancing (ablation) | PRISM-VO · drift study ablation | scale consistency and alignment | Improved |
| use PRISM-VO bundle adjustment instead of SPO projection from penultimate image | PRISM-VO · Plenoptic VO dataset | rotation error sequences: 3/7/8 -> 6/8/10 | Improved |
| use PRISM-VO instead of SPO | PRISM-VO · Plenoptic VO dataset | alignment error sequences: 2/6/9 -> 4/6/10 | Improved |
| use PRISM-VO instead of SPO | PRISM-VO · Plenoptic VO dataset | abs. scale error sequences: 5/7/9 -> 5/8/10 | Improved |
| use PRISM-VO instead of SPO | PRISM-VO · Plenoptic VO dataset | scale drift sequences: 7/8/9 -> 7/7/10 | No clear effect |
| use PRISM-VO instead of monocular ORB-SLAM3 | PRISM-VO · Plenoptic VO dataset | tracking success | Improved |
| use PRISM-VO instead of DSO | PRISM-VO · Plenoptic VO dataset | scale drift | Improved |
| use PRISM-VO instead of learning-based DPVO | PRISM-VO · Plenoptic VO dataset | alignment error | No clear effect |
| use PRISM-VO instead of DSO, ORB-SLAM3, DPVO | PRISM-VO · LiFMCR | RMSE_t: best RMSE_t on six out of seven sequences | Improved |
| use PRISM-VO instead of DPVO on scene 07 | PRISM-VO · LiFMCR scene 07 | RMSE_t: 5.87 -> 110.87 | Hurt |
| use PRISM-VO instead of baselines for rotation | PRISM-VO · LiFMCR | RMSE_r: best RMSE_r in four sequences | Mixed |
Closest papers by meaning
- Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction (CVPR 2018 · similarity 0.86)
- VOLDOR: Visual Odometry From Log-Logistic Dense Optical Flow Residuals (CVPR 2020 · similarity 0.86)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · similarity 0.86)
- COMO: Compact Mapping and Odometry (ECCV 2024 · similarity 0.86)
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (CVPR 2024 · similarity 0.86)
- Direct Sparse Odometry (TPAMI 2017 · 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.
