AI Paper Atlas

Research map / 3D vision / 3D generation

Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

Hyojun Go, Dominik Narnhofer, Goutam Bhat, Prune Truong, Federico Tombari, Konrad Schindler

ICLR 2026 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 11 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 model stitching of a 3D decoder to video VAE (Wan + AnySplat vs AnySplat alone) (ablation)AnySplat · RealEstate10K novel view synthesisPSNR: 20.85 -> 21.29Improved
add multi-view finetuning to the pretrained video model (ablation)Wan + AnySplat · SceneBenchImaging quality: 50.56 -> 54.56Improved
add 3D-consistency reward only to multi-view finetuning (ablation)Wan + AnySplat · SceneBenchImaging quality: 54.56 -> 38.67Hurt
add quality reward to multi-view finetuning (ablation)Wan + AnySplat · SceneBenchImaging quality: 54.56 -> 62.27Improved
add both quality and consistency rewards (full direct reward finetuning) over quality reward only (ablation)Wan + AnySplat · SceneBenchImaging quality: 62.27 -> 64.87Improved
add both rewards over quality reward only (ablation)Wan + AnySplat · SceneBenchAesthetic: 58.23 -> 56.96Hurt
add direct reward finetuning over multi-view only (ablation)Wan + AnySplat · SceneBenchUnified Reward Alignment: 3.622 -> 3.667Improved
choose stitching layer with lower linear stitching MSE (ablation)Wan + VGGT · 7-Scenes pointmapAcc./Comp./NCImproved
use CKA instead of MSE to pick the stitching layer (ablation)Wan + VGGT · 7-Scenes pointmapbest layer identificationHurt
use stitched latent decoder instead of sequential decode-then-VGGT under latent noise (ablation)stitched VGGT · ETH3D pointmapAcc./Comp./NC under noiseImproved
stitch Wan VAE to VGGT instead of using VGGT on imagesVGGT · 7-Scenes pointmapAccuracy mean: 0.020 -> 0.018No clear effect
stitch Wan VAE to MVDUSt3R instead of using MVDUSt3R on imagesMVDUSt3R · ETH3D pointmapAccuracy mean: 0.400 -> 0.401No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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