Research map / 3D vision / Depth and stereo
POMATO: Marrying Pointmap Matching with Temporal Motions for Dynamic 3D Reconstruction
Songyan Zhang, Yongtao Ge, Jinyuan Tian, Guangkai Xu, Hao Chen, Chen Lv, Chunhua Shen
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 temporal motion module (12-frame window) (ablation) | POMATO · Sintel video depth | Abs Rel: 0.548 -> 0.416 | Improved |
| add temporal motion module (12-frame window) (ablation) | POMATO · KITTI video depth | Abs Rel: 0.113 -> 0.086 | Improved |
| add temporal motion module (12-frame window) (ablation) | POMATO · PointOdyssey tracking | APD: 32.06 -> 33.20 | Improved |
| add temporal motion module (12-frame window) (ablation) | POMATO · PStudio tracking | APD: 23.10 -> 24.59 | Improved |
| increase temporal window from 6 to 12 frames (ablation) | POMATO · Sintel video depth | Abs Rel: 0.436 -> 0.416 | Improved |
| increase temporal window from 6 to 12 frames (ablation) | POMATO · KITTI video depth | Abs Rel: 0.085 -> 0.086 | No clear effect |
| add pointmap matching head (ablation) | POMATO · PointOdyssey tracking (pairwise) | APD: 29.10 -> 32.06 | Improved |
| add pointmap matching head (ablation) | POMATO · PStudio tracking (pairwise) | APD: 16.94 -> 23.10 | Improved |
| add pointmap matching head (ablation) | POMATO · Bonn pose | ATE: 0.040 -> 0.037 | Improved |
| add pointmap matching head (ablation) | POMATO · Bonn pose | RPE rot: 1.721 -> 1.782 | Hurt |
| POMATO vs SpatialTracker on 12-frame tracking | SpatialTracker · 3D tracking average | APD: 24.17 -> 29.79 | Improved |
| POMATO vs MonST3R on TUM pose | MonST3R · TUM pose | RPE rot: 1.142 -> 0.509 | Improved |
Later papers that compared with this method
3 later accepted papers report POMATO as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- 4D Primitive-Mache: Glueing Primitives for Persistent 4D Scene Reconstruction (CVPR 2026 · better on 2 of 2 shared results)
- Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow (ECCV 2026 · better on 1 of 2 shared results)
- Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels (ECCV 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- MonST3R — MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025) · better on 5 of 6 shared results
- SpatialTracker — SpatialTracker: Tracking Any 2D Pixels in 3D Space (CVPR 2024) · better on 2 of 2 shared results
- DUSt3R — DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024) · better on 1 of 1 shared result
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
- Enhancing 3D Reconstruction for Dynamic Scenes (NeurIPS 2025 · similarity 0.90)
- MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025 · similarity 0.89)
- Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos (CVPR 2025 · similarity 0.88)
- DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024 · similarity 0.86)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.86)
- Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments (CVPR 2024 · 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.
