AI Paper Atlas

Research map / Point clouds / Point cloud classification

Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion

Junru Lin, Chirag Vashist, Mikaela Angelina Uy, Colton Stearns, Xuan Luo, Leonidas Guibas, Ke Li

ICCV 2025 · Point clouds › Point cloud classification · approach: Scene flow and dynamic point clouds · 0 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 DINO input to the motion network (ablation)GMC · Synthetic global-motion scenesSI-FID: 203.38 -> 188.98Improved
add DINO input to the motion network (ablation)GMC · Synthetic global-motion scenesSI-MPED: 50.35 -> 26.05Improved
add position input to the motion network (ablation)GMC · Synthetic global-motion scenesSI-FID: 198.72 -> 188.98Improved
add position input to the motion network (ablation)GMC · Synthetic global-motion scenesSI-MPED: 54.29 -> 26.05Improved
add local isometry loss (ablation)GMC · Synthetic global-motion scenesSI-FID: 252.09 -> 188.98Improved
add local isometry loss (ablation)GMC · Synthetic global-motion scenesSI-MPED: 69.38 -> 26.05Improved
add joint refinement stage (ablation)GMC · Synthetic global-motion scenesSI-FID: 194.42 -> 188.98Improved
add joint refinement stage (ablation)GMC · Synthetic global-motion scenesSI-MPED: 28.08 -> 26.05Improved
use GMC instead of PAPR in Motion on large global motionGMC · Synthetic global-motion scenesSI-MPED: 114.45 -> 16.47Improved
use GMC instead of PAPR in Motion on small local motionGMC · Synthetic local-motion scenesSI-FID: 117.94 -> 112.62No clear effect
use GMC on real-world global motion vs PAPR in MotionGMC · Real-world global-motion scenesSI-EMD: 944.33 -> 70.85Improved
use GMC to refine sparse-view 3DGS (end state 10 views)GMC · Sparse+dense view NVSPSNR: 28.71 -> 33.07Improved

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