AI Paper Atlas

Research map / 3D vision / 3D generation

Auto-Regressively Generating Multi-View Consistent Images

JiaKui Hu, Yuxiao Yang, Jialun Liu, Jinbo Wu, Chen Zhao, Yanye Lu

ICCV 2025 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 8 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 Shuffle Views augmentation (ablation)MV-AR · GSO text-to-multi-viewFID: 173.51 -> 144.29Improved
add Shuffle Views augmentation (ablation)MV-AR · GSO text-to-multi-viewIS: 4.77 -> 8.00Improved
add Shuffle Views augmentation (ablation)MV-AR · GSO image-to-multi-viewPSNR: 18.27 -> 22.99Improved
add shift position embedding from camera pose (ablation)MV-AR · GSO text-to-multi-viewFID: 147.29 -> 144.29Improved
add shift position embedding from camera pose (ablation)MV-AR · GSO image-to-multi-viewPSNR: 21.30 -> 22.99Improved
use Image Warp Controller instead of in-context image condition (ablation)MV-AR · GSO image-to-multi-viewPSNR: 11.92 -> 22.99Improved
use Image Warp Controller instead of cross attention (ablation)MV-AR · GSO image-to-multi-viewLPIPS: 0.310 -> 0.084Improved
use Split Self-Attention for text condition instead of plain self-attention (ablation)MV-AR · GSO text-to-multi-viewCLIP-Score: 28.36 -> 29.49Improved
use Split Self-Attention for text condition instead of plain self-attention (ablation)MV-AR · GSO text-to-multi-viewIS: 5.78 -> 8.00Improved
use Split Self-Attention (MV-AR) instead of plain self-attention (ablation)MV-AR · GSO text-to-multi-viewFID: 146.11 -> 144.29Improved
auto-regressive MV-AR instead of diffusion MVDreamMV-AR · GSO text-to-multi-viewFID: 141.05 -> 144.29Hurt
auto-regressive MV-AR instead of diffusion Wonder3DMV-AR · GSO image-to-multi-viewLPIPS: 0.062 -> 0.084Hurt

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