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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Xinyue, Ma, Zhiyuan, Sun, Lingchen, Guo, Yanjun, Zhang, Lei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909923630120960
author Liang, Xinyue
Ma, Zhiyuan
Sun, Lingchen
Guo, Yanjun
Zhang, Lei
author_facet Liang, Xinyue
Ma, Zhiyuan
Sun, Lingchen
Guo, Yanjun
Zhang, Lei
contents Single-image-to-3D models typically follow a sequential generation and reconstruction workflow. However, intermediate multi-view images synthesized by pre-trained generation models often lack cross-view consistency (CVC), significantly degrading 3D reconstruction performance. While recent methods attempt to refine CVC by feeding reconstruction results back into the multi-view generator, these approaches struggle with noisy and unstable reconstruction outputs that limit effective CVC improvement. We introduce AlignCVC, a novel framework that fundamentally re-frames single-image-to-3D generation through distribution alignment rather than relying on strict regression losses. Our key insight is to align both generated and reconstructed multi-view distributions toward the ground-truth multi-view distribution, establishing a principled foundation for improved CVC. Observing that generated images exhibit weak CVC while reconstructed images display strong CVC due to explicit rendering, we propose a soft-hard alignment strategy with distinct objectives for generation and reconstruction models. This approach not only enhances generation quality but also dramatically accelerates inference to as few as 4 steps. As a plug-and-play paradigm, our method, namely AlignCVC, seamlessly integrates various multi-view generation models with 3D reconstruction models. Extensive experiments demonstrate the effectiveness and efficiency of AlignCVC for single-image-to-3D generation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23150
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
Liang, Xinyue
Ma, Zhiyuan
Sun, Lingchen
Guo, Yanjun
Zhang, Lei
Computer Vision and Pattern Recognition
Single-image-to-3D models typically follow a sequential generation and reconstruction workflow. However, intermediate multi-view images synthesized by pre-trained generation models often lack cross-view consistency (CVC), significantly degrading 3D reconstruction performance. While recent methods attempt to refine CVC by feeding reconstruction results back into the multi-view generator, these approaches struggle with noisy and unstable reconstruction outputs that limit effective CVC improvement. We introduce AlignCVC, a novel framework that fundamentally re-frames single-image-to-3D generation through distribution alignment rather than relying on strict regression losses. Our key insight is to align both generated and reconstructed multi-view distributions toward the ground-truth multi-view distribution, establishing a principled foundation for improved CVC. Observing that generated images exhibit weak CVC while reconstructed images display strong CVC due to explicit rendering, we propose a soft-hard alignment strategy with distinct objectives for generation and reconstruction models. This approach not only enhances generation quality but also dramatically accelerates inference to as few as 4 steps. As a plug-and-play paradigm, our method, namely AlignCVC, seamlessly integrates various multi-view generation models with 3D reconstruction models. Extensive experiments demonstrate the effectiveness and efficiency of AlignCVC for single-image-to-3D generation.
title AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.23150