Research map / 3D vision / Depth and stereo
IDOL: Inertial Deep Orientation-Estimation and Localization
Scott Sun, Dennis Melamed, Kris Kitani
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 EKF fusion to OrientNet (ablation) | OrientNet · Building 1 | orientation RMSE (radians): 0.21 -> 0.08 | Improved |
| Add EKF fusion to OrientNet (ablation) | OrientNet · Building 2 | orientation RMSE (radians): 0.44 -> 0.10 | Improved |
| Add EKF fusion to OrientNet (ablation) | OrientNet · Building 3 | orientation RMSE (radians): 0.49 -> 0.14 | Improved |
| Use IDOL orientation instead of API orientation | RoNIN-LSTM · Building 1 | ATE: 18.41 -> 7.03 | Improved |
| Use IDOL orientation instead of API orientation | RoNIN-TCN · Building 1 | T-RTE: 6.13 -> 2.56 | Improved |
| Use IDOL orientation instead of API orientation | RoNIN-ResNet · Building 1 | ATE: 10.48 -> 5.66 | Improved |
| Use IDOL orientation instead of API orientation | TLIO · Building 1 | T-RTE: 3.33 -> 2.39 | Improved |
| Use IDOL orientation instead of API orientation | RoNIN-LSTM · Building 1 | ATE: 18.41 -> 7.03; 6.53 with true orientation | Mixed |
| Use IDOL orientation instead of API orientation | TLIO · Building 1 | D-RTE: 0.38 -> 0.29 | Improved |
| Train separately for each building | IDOL · Building 2 | D-RTE: 0.41 vs 0.33 | Hurt |
Later papers that compared with this method
9 later accepted papers report IDOL as a baseline in their results tables; 9 of them report a better number on most of the results they share with it.
- Bringing Your Portrait to 3D Presence (CVPR 2026 · better on 8 of 9 shared results)
- Zero-Shot Reconstruction of Animatable 3D Avatars with Cloth Dynamics from a Single Image (CVPR 2026 · better on 9 of 9 shared results)
- CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Image (CVPR 2026 · better on 7 of 7 shared results)
- AHOY! Animatable Humans under Occlusion from YouTube Videos with Gaussian Splatting and Video Diffusion Priors (ECCV 2026 · better on 6 of 6 shared results)
- DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion (ECCV 2026 · better on 6 of 6 shared results)
- SplatCtrlA: Generalizable Single Image to Fully Controllable 3D Avatar (ECCV 2026 · better on 6 of 6 shared results)
- LUNA: Learning Universal 3D Human Animation Beyond Skinning (ECCV 2026 · better on 4 of 4 shared results)
- NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses (NeurIPS 2025 · better on 6 of 6 shared results)
1 more not listed.
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
- Tartan IMU: A Light Foundation Model for Inertial Positioning in Robotics (CVPR 2025 · similarity 0.86)
- EqNIO: Subequivariant Neural Inertial Odometry (ICLR 2025 · similarity 0.85)
- iMoT: Inertial Motion Transformer for Inertial Navigation (AAAI 2025 · similarity 0.83)
- MODA: Motion-Drift Augmentation for Inertial Human Motion Analysis (CVPR 2025 · similarity 0.83)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · similarity 0.83)
- Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning (CVPR 2024 · similarity 0.83)
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.
