Research map / 3D vision / Depth and stereo
Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning
Mengtan Zhang, Zizhan Guo, Hongbo Zhao, Yi Feng, Zuyi Xiong, Yue Wang, Shaoyi Du, Hanli Wang, Rui Fan
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 |
|---|---|---|---|
| train with DiMoDE discriminative motion-component treatment instead of previous SoTA | previous SoTA learning-based VO · KITTI Odometry Seq. 00 | ATE: 75.05% reduction | Improved |
| train with DiMoDE instead of previous SoTA | previous SoTA learning-based VO · KITTI Odometry Seq. 02 | ATE: 65.30% reduction | Improved |
| train with DiMoDE instead of previous SoTA | previous SoTA learning-based VO · KITTI Odometry Seq. 05 | ATE: 52.11% reduction | Improved |
| train with DiMoDE instead of previous SoTA | previous SoTA learning-based VO · KITTI Odometry Seq. 08 | ATE: 54.56% reduction | Improved |
| use DiMoDE instead of SCIPaD (finetuned) | SCIPaD · KITTI Odometry Seqs. 11-20 | ATE: 35.78 -> 26.64 | Improved |
| use DiMoDE instead of Lite-Mono baseline depth training | Lite-Mono · KITTI depth (640x192) | Abs Rel: 0.101 -> 0.097 | Improved |
| DiMoDE versus geometry-based ORB-SLAM3 | DiMoDE · KITTI Odometry Seqs. 11-20 | ATE: 13.46 -> 26.64 | Hurt |
Closest papers by meaning
- SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-Motion (ICCV 2019 · similarity 0.92)
- Unsupervised Learning of Depth and Ego-Motion From Monocular Video Using 3D Geometric Constraints (CVPR 2018 · similarity 0.91)
- EgoMo3R: Joint Egocentric Motion and Scene Reconstruction (NeurIPS 2026 · similarity 0.90)
- E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization (NeurIPS 2025 · similarity 0.89)
- Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos (CVPR 2025 · similarity 0.88)
- Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video (ICLR 2025 · 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.
