用跨空间去噪快速生成零样本3D视觉错觉，视角不同内容迥异。
JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising
- 分两阶段生成：先跨空间去噪融合几何，再视图条件合成纹理
- 3-5分钟生成双语义3D模型，几何完整且语义清晰可辨
- 无需训练，适合快速创作多视角视觉魔术场景
生成3D视觉错觉——一个从不同视角看呈现完全不同语义的单个3D网格——是一项既迷人又具挑战的任务。现有基于优化的方法速度慢且颜色过饱和；而简单的拼接方法则难以保证几何一致性，导致明显的人工接缝和语义泄露。本文提出一种快速、无需训练的文本驱动3D视觉错觉生成框架。方法分为两个阶段：首先，提出跨空间双分支去噪过程，动态将3D隐变量解码至体素空间，通过CLIP引导对齐方向并融合符号距离场（SDF），确保几何无缝融合；其次，引入视图条件纹理合成模块，将视图相关的2D扩散先验投影并聚合到融合后的几何上。大量实验表明，本方法仅需3-5分钟即可生成高度真实的双语义3D视觉错觉，在几何完整性、语义可识别性与效率上显著优于现有方法。
原文摘要 · Abstract (English)
Creating 3D visual illusions, a single 3D mesh that reveals entirely different semantics from various viewing angles, is a fascinating but tough challenge. Existing optimization-based methods are slow and can produce oversaturated colors. In contrast, naive stitching approaches fail to produce geometrically coherent objects. This results in visible unnatural seams and semantic leaks. In this paper, we present a fast and training-free framework for generating text-driven 3D visual illusions. Our approach decouples the generation into two stages. First, we propose a cross-space dual-branch denoising process. This process dynamically decodes 3D latents into voxel space for CLIP-guided orientation alignment and Signed Distance Field (SDF) blending, which ensures seamless geometric fusion. Second, we introduce a view-conditioned texture synthesis module that projects and aggregates view-specific 2D diffusion priors onto the fused geometry. Extensive experiments demonstrate that our method generates highly realistic, dual-semantic 3D illusions in just 3-5 minutes. It significantly outperforms existing methods in geometric integrity, semantic recognizability, and efficiency. Project page: https://siang1105.github.io/JanusMesh.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。