AI Paper Atlas

Research map / 3D vision / Gaussian splatting

RetrievalFuse: Neural 3D Scene Reconstruction With a Database

Yawar Siddiqui, Justus Thies, Fangchang Ma, Qi Shan, Matthias Nießner, Angela Dai

ICCV 2021 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 32 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 attention blending instead of naive feature concatenation (ablation)RetrievalFuse · 3DFront 3D super-resolutionIoU: 0.71 -> 0.75Improved
add attention blending instead of naive feature concatenation (ablation)RetrievalFuse · 3DFront surface reconstructionIoU: 0.84 -> 0.86Improved
add retrievals to refinement compared with a U-Net without retrievals (ablation)RetrievalFuse · 3DFront 3D super-resolutionIoU: 0.68 -> 0.75Improved
add retrievals to refinement compared with a U-Net without retrievals (ablation)RetrievalFuse · 3DFront surface reconstructionIoU: 0.83 -> 0.86Improved
add refinement on top of 1-NN retrieval (ablation)RetrievalFuse · 3DFront 3D super-resolutionIoU: 0.67 -> 0.75Improved
increase retrieved chunks k from 0 to 4 (ablation)RetrievalFuse · 3DFront 3D super-resolutionIoU: 0.684 -> 0.751Improved
use smaller retrieval chunks (3.467m to 0.867m) (ablation)RetrievalFuse · 3DFront 3D super-resolutionIoU: 0.71 -> 0.75Improved
increase database train scenes from 25% to 100% (ablation)RetrievalFuse · 3DFront 3D super-resolutionIoU: 0.711 -> 0.751Improved
extend database at test time with chunks of new classes (ablation)RetrievalFuse · ShapeNet 8 -> 5 unseen classesIoU: 0.478 -> 0.579Improved
add retrieval-based reconstruction to IFNetIFNet · 3DFront 3D super-resolutionIoU: 0.639 -> 0.687Improved
use attention instead of naive fusion when retrievals are suboptimal (ablation)RetrievalFuse · ShapeNet 8 -> 5 unseen classesIoU: 0.432 -> 0.478; backbone 0.463Mixed
RetrievalFuse vs IFNet on Matterport3D surface reconstructionRetrievalFuse · Matterport3D surface reconstructionIoU: 0.575 -> 0.710Improved

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