AI Paper Atlas

Research map / 3D vision / 3D generation

GeoNVS: Geometry Grounded Video Diffusion for Novel View Synthesis

Minjun Kang, Inkyu Shin, Taeyeop Lee, Myungchul Kim, In Kweon, KUK-JIN YOON

ECCV 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 2 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 GS-Adapter feature-space geometry guidance to SEVASEVA · Small-viewpoint set (average)PSNR: 17.15 -> 19.09Improved
add GS-Adapter to SEVA on large-viewpoint setSEVA · Large-viewpoint set (average)PSNR: 12.64 -> 14.20Improved
add GS-Adapter to SEVA for long trajectoriesSEVA · Long trajectory DL3DV (P=9)PSNR: 16.73 -> 19.32Improved
add GS-Adapter to SEVA, camera pose and geometrySEVA · RE10K (P=3)Translation error: 1.62 -> 0.76Improved
add GS-Adapter to SEVA, Chamfer distanceSEVA · RE10K (P=3)Chamfer distance: 1.35 -> 0.19Improved
replace feature-space guidance with input-level injection of 3D Gaussian rendersSEVA · DL3DV (6 reference views)Translation error: 19.68 -> 81.14Hurt
use Difix3D input-level geometry integration instead of GS-AdapterSEVA · DL3DV (6 reference views)Chamfer distance: 0.57 -> 3.76Hurt
add GS-Adapter to improve unseen-region qualitySEVA · DL3DV (6 reference views)PSNR_U: +2.08Improved
use adaptive fusion instead of naive fusion with Pi3 prior (ablation)GeoNVS (SEVA) · DTU (3 reference views)PSNR: 14.83 -> 19.02Improved
use adaptive fusion instead of naive fusion with VGGT prior (ablation)GeoNVS (SEVA) · DTU (3 reference views)PSNR: 18.89 -> 19.18Improved
add adaptive fusion (vs naive fusion) (ablation)GS-Adapter (VGGT prior) · Mip360 6-viewPSNR: 16.48 -> 16.57Improved
add feature consistency loss L_feat (ablation)GS-Adapter (VGGT prior) · Mip360 6-viewPSNR: 16.47 -> 16.48Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 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.

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