AI Paper Atlas

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

ICCV 2025 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 23 citations (OpenAlex)

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 changedWhereMeasuredEffect
add temporal motion module (12-frame window) (ablation)POMATO · Sintel video depthAbs Rel: 0.548 -> 0.416Improved
add temporal motion module (12-frame window) (ablation)POMATO · KITTI video depthAbs Rel: 0.113 -> 0.086Improved
add temporal motion module (12-frame window) (ablation)POMATO · PointOdyssey trackingAPD: 32.06 -> 33.20Improved
add temporal motion module (12-frame window) (ablation)POMATO · PStudio trackingAPD: 23.10 -> 24.59Improved
increase temporal window from 6 to 12 frames (ablation)POMATO · Sintel video depthAbs Rel: 0.436 -> 0.416Improved
increase temporal window from 6 to 12 frames (ablation)POMATO · KITTI video depthAbs Rel: 0.085 -> 0.086No clear effect
add pointmap matching head (ablation)POMATO · PointOdyssey tracking (pairwise)APD: 29.10 -> 32.06Improved
add pointmap matching head (ablation)POMATO · PStudio tracking (pairwise)APD: 16.94 -> 23.10Improved
add pointmap matching head (ablation)POMATO · Bonn poseATE: 0.040 -> 0.037Improved
add pointmap matching head (ablation)POMATO · Bonn poseRPE rot: 1.721 -> 1.782Hurt
POMATO vs SpatialTracker on 12-frame trackingSpatialTracker · 3D tracking averageAPD: 24.17 -> 29.79Improved
POMATO vs MonST3R on TUM poseMonST3R · TUM poseRPE rot: 1.142 -> 0.509Improved

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.

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy