AI Paper Atlas

Research map / 3D vision / Depth and stereo

MV-TAP: Tracking Any Point in Multi-View Videos

Jahyeok Koo, Inès Hyeonsu Kim, Mungyeom Kim, Junghyun Park, Seohyeon Park, Jaeyeong Kim, Jung Yi, Seokju Cho, Seungryong Kim

CVPR 2026 · 3D vision › Depth and stereo · approach: Learned optical and scene flow · 4 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 view attention and camera embedding to CoTracker3 (MV-TAP) (ablation)CoTracker3 · DexYCB (8 views)AJ: 41.5 -> 44.2Improved
add view attention to CoTracker3 (ablation)CoTracker3 · Panoptic StudioAJ: 39.6 -> 38.6Hurt
add view attention to CoTracker3 (ablation)CoTracker3 · DexYCBAJ: 41.5 -> 43.6Improved
add camera embedding to view attention (ablation)MV-TAP · Panoptic StudioAJ: 38.6 -> 40.3Improved
add camera embedding to view attention (ablation)MV-TAP · DexYCBAJ: 43.6 -> 44.2Improved
increase number of input views from 2 to 8 (ablation)MV-TAP · DexYCBAJ: 39.2 -> 44.2Improved
increase number of input views from 2 to 8 (ablation)CoTracker3 · DexYCBAJ: 37.5 -> 41.5Improved
flatten view and time dimensions in CoTracker3CoTracker3 · DexYCB (8 views)AJ: 41.5 -> 2.7Hurt
add triangulation-based refinement to CoTracker3CoTracker3 · DexYCB (in-frame occluded points)position accuracy on occluded points: 33.9 -> 34.8Improved
add triangulation-based refinement to CoTracker3CoTracker3 · DexYCB (8 views)position accuracy (<d_avg): 59.6 -> 57.1Hurt
MV-TAP versus additionally trained CoTracker3 (ablation)MV-TAP · DexYCBAJ: 41.8 -> 44.2Improved
MV-TAP on frequently occluded trajectoriesCoTracker3 · DexYCB (frequently occluded trajectories)AJ: 26.2 -> 29.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 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