AI Paper Atlas

Research map / 3D vision / 3D generation

AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation

Xinyue Liang, Zhiyuan Ma, Lingchen Sun, Yanjun Guo, Lei Zhang

AAAI 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 3 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 score-distillation soft alignment for the MVG model (ablation)AlignCVC (Wonder3D+LGM) · GSOPSNR: 18.28 -> 21.98Improved
add adversarial hard alignment for the reconstruction model (ablation)AlignCVC (Wonder3D+LGM) · GSOPSNR: 20.84 -> 21.98Improved
add regression loss LRecon alongside distribution alignment (ablation)AlignCVC (Wonder3D+LGM) · GSOPSNR: 21.04 -> 21.98Improved
joint training of MVG and reconstruction instead of fixing either (ablation)AlignCVC (Wonder3D+LGM) · GSOPSNR: Fixed MVG 17.40, Fixed Recon. 19.05 -> 21.98Improved
apply 3D-aware sampling to pre-trained models without alignment training (ablation)Wonder3D+LGM · GSOFID: 189.97 -> 249.05Hurt
fine-tune only the reconstruction model on inconsistent generated views (ablation)Wonder3D+LGM two-stage · GSOPSNR / SSIM / FID: PSNR 16.89 -> 18.24; SSIM 0.72 -> 0.66; FID 189.97 -> 194.44Mixed
use adversarial hard alignment for the MVG model instead of score distillation (ablation)AlignCVC · GSOPSNR: 21.98 -> 17.31Hurt
use score distillation (soft alignment) for the reconstruction model instead of GAN (ablation)AlignCVC · GSOPSNR: 21.98 -> 16.69Hurt
replace distillation loss with diffusion loss for MVG (ablation)AlignCVC · GSOPSNR: 21.98 -> 16.39Hurt
apply AlignCVC alignment training to pre-trained MVG+reconstruction pairsWonder3D+LaRa · GSOFID: 220.770 -> 158.699Improved
apply AlignCVC with 4-step inference vs prior 3D-aware samplingWonder3D+LGM · GSOinference time (s): 41.52 (Gen-3Diffusion) -> 8.87Improved

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