AI Paper Atlas

Research map / 3D vision / Depth and stereo

PAGE-4D: Disentangled Pose and Geometry Estimation for 4D Perception

Kaichen Zhou, Yuhan Wang, Grace Chen, Gaspard Beaudouin, Fangneng Zhan, Paul Pu Liang, Mengyu Wang

ICLR 2026 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence

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 dynamics-aware mask attention to middle-layer fine-tuning (ablation)PAGE-4D (VGGT*) · Sintel video depth (scale align)Abs Rel: 0.409 -> 0.357Improved
add dynamics-aware mask attention to middle-layer fine-tuning (ablation)PAGE-4D (VGGT*) · Sintel video depth (scale align)delta<1.25: 0.590 -> 0.699Improved
add dynamics-aware mask attention to middle-layer fine-tuning (ablation)PAGE-4D (VGGT*) · DyCheck video depth (scale align)Abs Rel: 0.177 -> 0.170Improved
fine-tune only middle layers instead of whole model (ablation)VGGT* · Sintel video depth (scale align)Abs Rel: 0.405 -> 0.409No clear effect
fine-tune with dynamic-aware aggregator vs plain VGGTVGGT · Sintel camera poseATE: 0.214 -> 0.178Improved
fine-tune with dynamic-aware aggregator vs plain VGGTVGGT · DyCheck point reconstructionAccuracy error (mean): 1.051 -> 0.403Improved
fine-tune with dynamic-aware aggregator vs plain VGGTVGGT · Nerfie novel view synthesisPSNR: 16.861 -> 17.593Improved
mask dynamic tokens attention (DD-MSK) on VGGT (ablation)VGGT · OdysseyRPE rot / Static-D: RPE rot 0.942 -> 0.869; Static-D 0.085 -> 0.566Mixed
mask dynamic regions at input (Input-MSK) on VGGT (ablation)VGGT · OdysseyRPE rot: 0.942 -> 1.006Hurt
replace layer 17 global attention output with noise (ablation)VGGT · OdysseyStatic-D: 0.085 -> 1.663Hurt

Earlier methods this paper compares with

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