3D幻觉物体：一个模型，两个视角，两种含义
你见过一个雕塑，从左边看是猫，从右边看是狗吗？这就是3D视觉幻觉。以前做这种东西，要么慢得像蜗牛（优化几小时），要么颜色过饱和像卡通，要么接缝明显像拼贴画。这篇论文搞了个新方法，3-5分钟就能生成一个逼真的3D物体，从不同角度看，它呈现完全不同的语义——比如一个花瓶，转45度变成人脸。核心是两步走：先通过一个双分支去噪过程，在3D空间里同时对齐两个视角的语义，并让几何形状无缝融合；再根据视角生成对应的纹理，贴到融合后的模型上。结果就是：几何完整、语义清晰、速度快。它不是你明天就能用的工具，但让你看到AI在创意生成上的新可能——一个物体，多个故事。
📄 原文摘要(英文)
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/