AI Paper Atlas

Research map / 3D vision / 3D generation

GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising

Yi He, Jiangming Wang, Xinyu Wang, Mark Fong, Songchun Zhang, Yuxuan Xue, Hai-Tao Zheng, Yue Ma

ECCV 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 1 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 variance-homogeneous injection (vs uncalibrated constraints) (ablation)GeoEdit · GeoEditBenchDINO: 0.314 -> 0.961Improved
add warm-start initialization (ablation)GeoEdit · GeoEditBenchPSNR: 21.320 -> 23.499Improved
use dual-branch window (47,40) instead of single-timestep init at 47 (ablation)GeoEdit · GeoEditBenchPSNR: 20.724 -> 23.499Improved
use dual-branch window (47,40) instead of low-noise init at 40 (ablation)GeoEdit · GeoEditBenchCLIP: 0.906 -> 0.952Improved
restrict proxy injection to a window instead of all timesteps (ablation)GeoEdit · GeoEditBenchDINO: 0.860 -> 0.961Improved
start from warm-start proxy instead of pure noise (ablation)GeoEdit · GeoEditBenchPSNR: 18.479 -> 23.499Improved
avoid excessive proxy injection (t=1) (ablation)GeoEdit · GeoEditBenchDreamSim: 0.084 -> 0.027Improved
add variance matching to injection (ablation)GeoEdit · attention leakage at t=46ALR: 8.4% -> 6.4%Improved
use full 81-frame video context instead of 1/21/41/61 (ablation)GeoEdit · visual ablationstructural integrityImproved
GeoEdit vs NanoBanana on identity (CLIP)GeoEdit · GeoEditBenchCLIP: 0.976 -> 0.952Hurt
GeoEdit vs strongest baselines on geometry metricsGeoEdit · GeoEditBenchObject IoU: 51.3% (Flux-Kontext) -> 57.9%Improved
GeoEdit vs 3DitScene on external benchmarkGeoEdit · 3DEdit-BenchObject IoU: 0.310 -> 0.460Improved

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