Research map / 3D vision / Depth and stereo
LivePose: Online 3D Reconstruction from Monocular Video with Dynamic Camera Poses
Noah Stier, Baptiste Angles, Liang Yang, Yajie Yan, Alex Colburn, Ming Chuang
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 de-integration before re-integration on pose updates (ablation) | DeepVideoMVS · ScanNet with LivePose | F-score: 0.535 -> 0.554 | Improved |
| add de-integration before re-integration on pose updates (ablation) | Atlas · ScanNet with LivePose | F-score: 0.545 -> 0.564 | Improved |
| add learned non-linear de-integration to NeuralRecon (ablation) | NeuralRecon · ScanNet with LivePose | F-score: 0.568 -> 0.577 | Improved |
| respond to pose updates (re-integration only) vs ignoring updates (ablation) | Atlas · ScanNet with LivePose | F-score: 0.531 -> 0.545 | Improved |
| learned de-integration instead of reconstructing from scratch (ablation) | NeuralRecon · ScanNet with LivePose | F-score: 0.581 -> 0.577 | No clear effect |
| train NeuralRecon on LivePose dynamic poses (ablation) | NeuralRecon · ScanNet with LivePose | F-score: 0.544 -> 0.581 | Improved |
| use fusion network instead of pair network for DeepVideoMVS (ablation) | DeepVideoMVS · ScanNet with LivePose | F-score: 0.515 -> 0.554 | Improved |
| re-compute depth before re-integration (ablation) | DeepVideoMVS · ScanNet with LivePose | F-score: 0.554 -> 0.545 | No clear effect |
Closest papers by meaning
- SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos (CVPR 2025 · similarity 0.90)
- ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos (NeurIPS 2025 · similarity 0.90)
- VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold (NeurIPS 2025 · similarity 0.88)
- MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors (CVPR 2025 · similarity 0.87)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.87)
- MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos (CVPR 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.
