AI Paper Atlas

Research map / 3D vision / Human pose estimation

PosePlaner: Denoising Any Feedforward Pose Predictor from Pairwise Planar Geometry

Yihang Chen, Bin Tan, Yujun Shen, Yinghao Xu, Nan Xue

NeurIPS 2026 · 3D vision › Human pose estimation · approach: Learned camera pose estimation

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes PosePlaner, a method that denoises feedforward multi-view pose predictors (e.g., DUSt3R, VGGT) using pairwise planar geometry, based only on the abstract provided.

Problem

Multi-view feedforward Transformers such as DUSt3R and VGGT subsume the classical SfM/SLAM pipeline in one pass, which hides the interfaces between correspondences, geometry, and pose, making their pose estimates entangled and hard to refine.

Approach

Exposes the intermediate pipeline interfaces by denoising feedforward pose predictions using pairwise planar geometry, applicable to any feedforward pose predictor. Details beyond the abstract are unavailable.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
refine weak LoFTR poses with PosePlanerLoFTR · ScanNet1500rotation AUC@5: 11.5 -> 29.4Improved
refine strong ROMA/MASt3R poses with PosePlanerROMA, MASt3R · ScanNet1500rotation AUC@5: 66.7 -> 64.1 (ROMA); 66.5 -> 65.0 (MASt3R)Hurt
refine streaming estimators at long sequence lengthCUT3R · ScanNet streaming N=2000rotation AUC@5: 17.3 -> 37.3Improved
refine streaming estimators at short sequence lengthTTT3R · ScanNet streaming N=200translation AUC@5: 11.1 -> 10.8No clear effect
replace NopeSAC head with PosePlanercorrespondence-based solvers · ScanNet1500rotation AUC@5: 34.9 -> 48.9 (SuperGlue)Improved
use PosePlaner instead of bundle adjustmentLoFTR init · ScanNet1500rotation AUC@5: 13.4 -> 29.5Improved
use PosePlaner instead of bundle adjustmentMASt3R init · ScanNet1500rotation AUC@5: 66.5 -> 64.7Hurt
add geometry tokens g_m as conditioning (ablation)PosePlaner · ScanNet1500 (LoFTR init)rotation AUC@5: 11.5 -> 29.4Improved
add pose token c (upstream init) as conditioning (ablation)PosePlaner · ScanNet1500rotation AUC@5: 17.4 -> 48.9 (SuperGlue init)Improved
add score-head fusion instead of uniform averaging (ablation)PosePlaner · ScanNet1500 (LoFTR init)rotation AUC@5: 26.5 -> 29.4Improved
add translation channel to the diffusion residual (ablation)PosePlaner · ScanNet1500 (LoFTR init)rotation AUC@5: 16.4 -> 29.4Improved
use 6D rotation instead of unit quaternion (ablation)PosePlaner · ScanNet1500 (LoFTR init)rotation AUC@5: 20.4 -> 29.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 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.

Experimental setup

Builds on: DUSt3R VGGT

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