AI Paper Atlas

Research map / 3D vision / 3D generation

Align Images Before You Generate

Shihua Zhang, Qiuhong Shen, Xinchao Wang

CVPR 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D

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 training-free CorrAdapterMVAdapter · Image-conditioned multi-view (GSO)MEt3R: 0.2116 -> 0.2036Improved
add training-free CorrAdapterSyncDreamer · Image-conditioned multi-view (GSO)depth error: 14.15 -> 12.60Improved
add training-free CorrAdapterSyncDreamer · Image-conditioned multi-view (GSO)Chamfer Distance: 2.66 -> 2.67No clear effect
add optional consistency-loss training schemeMVAdapter+CorrAdapter · Image-conditioned multi-view (GSO)cPSNR: 19.68 -> 20.47Improved
add optional training schemeMVAdapter+CorrAdapter · Text-conditioned multi-view (Objaverse)FID: 23.42 -> 24.17; IS 15.96 -> 17.07Mixed
add CorrAdapterWan2.1-1.3B · Text-to-video (VBench)Subject Consistency: 0.9536 -> 0.9715Improved
add CorrAdapterWan2.1-1.3B · Text-to-video (VBench)Dynamic Degree: 0.5556 -> 0.5139Hurt
train CorrAdapter end-to-end with consistency loss instead of fine-tuning first then adding module (ablation)MVAdapter+CorrAdapter · Image-conditioned multi-view (GSO)PSNR: 24.05 -> 23.65Hurt
add CorrAdapterMVAdapter · Runtimepeak memory (GB): 15.27 -> 20.86Hurt

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