AI Paper Atlas

Research map / 3D vision / Gaussian splatting

CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels

Jirong Li, Satoshi Ikehata, Shuhei Kurita, Ikuro Sato

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 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 camera pose refinement with pseudo-label losses after retrieval (ablation)CapFrame · Mip-NeRF 360SigLIP2: 0.121 -> 0.244Improved
add camera pose refinement (ablation)CapFrame · LERF-OVSSigLIP2: 0.503 -> 0.708Improved
add camera pose refinement (ablation)CapFrame · Tanks and TemplesSigLIP2: 0.307 -> 0.339Improved
CapFrame vs best heuristic baseline SVSCapFrame · TIVGGPT alignment score: 4.06 -> 4.75Improved
remove orientation pseudo label (ablation)CapFrame · TIVGrotation deviation / SigLIP2: dR 33.71 deg; dSigLIP2 -0.128Hurt
remove layout pseudo label (ablation)CapFrame · TIVGtranslation deviation / SigLIP2: dt 5.701; dSigLIP2 -0.236Hurt
use Top-5 instead of Top-2 retrieved images for initialization (ablation)CapFrame · TIVGSigLIP2: dSigLIP2 -0.165Hurt
paraphrase the input instruction (ablation)CapFrame · TIVGSigLIP2: dSigLIP2 +0.032No clear effect
add moderate noise to pseudo labels (ablation)CapFrame · TIVGSigLIP2: dSigLIP2 -0.048No clear effect
add Question-Evaluation to FG-CLIP retrieval (ablation)CapFrame · TIVG retrievalinitial view qualityImproved
optimize pose at low resolution (ablation)CapFrame · TIVG runtimetime per query: 102.5 s -> 55.8 sImproved

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