AI Paper Atlas

Research map / 3D vision / 3D generation

DiGA3D: Coarse-to-Fine Diffusional Propagation of Geometry and Appearance for Versatile 3D Inpainting

Jingyi Pan, Dan Xu, Qiong Luo

ICCV 2025 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 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 TG-SDS loss (fine stage) (ablation)DiGA3D · Object removal (SPIn-NeRF)PSNR: 20.66 -> 20.71Improved
add TG-SDS loss (fine stage) (ablation)DiGA3D · Object removal (SPIn-NeRF)LPIPS: 0.29 -> 0.28Improved
add TG-SDS loss (fine stage) (ablation)DiGA3D · Object removal (SPIn-NeRF)SSIM: 0.57 -> 0.58Improved
add AFP and DDIM inversion in 2D inpainter (coarse stage) (ablation)DiGA3D · Object removal (SPIn-NeRF)PSNR: 20.45 -> 20.66Improved
add AFP and DDIM inversion in 2D inpainter (coarse stage) (ablation)DiGA3D · Object removal (SPIn-NeRF)LPIPS: 0.30 -> 0.29Improved
increase reference views K from 1 to 3 (ablation)DiGA3D · SPIn-NeRF Scene 1PSNR: 19.87 -> 19.94Improved
increase reference views K from 1 to 3 (ablation)DiGA3D · SPIn-NeRF Scene 1memory (GB): 41G -> 47GHurt
increase reference views K from 2 to 3 (ablation)DiGA3D · SPIn-NeRF Scene 1LPIPS: 0.3412 -> 0.3330Improved
select reference views by K-means instead of randomly (ablation)DiGA3D · Object removal (SPIn-NeRF)consistencyImproved
select reference views by K-means instead of randomly (coarse stage) (ablation)DiGA3D · Object removal (SPIn-NeRF)consistencyNo clear effect
DiGA3D vs GScream on masked LPIPSGScream · Object removal (SPIn-NeRF)Masked LPIPS: 0.54 -> 0.56Hurt
DiGA3D vs GaussCtrl for re-texturingGaussCtrl · Object re-texturingCLIP_dir: 0.0742 -> 0.1751Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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