JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising

• URL: http://arxiv.org/abs/2606.20563v1
• Date: Thu, 18 Jun 2026 17:59:55 GMT
• Title: JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising
• Abstract summary: We present a framework for generating text-driven 3D visual illusions.<n>Our method generates highly realistic, dual-semantic 3D illusions in just 3-5 minutes.<n>It significantly outperforms existing methods in geometric integrity, semantic recognizability, and efficiency.
• Score: 4.625351881266883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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/

Related papers

• OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder [90.8453349494245]
  We present OneWorld, a framework that performs diffusion directly within a coherent 3D representation space.<n>OneWorld generates high-quality 3D scenes with superior cross-view consistency compared to state-of-the-art 2D-based methods.
  arXiv  Detail & Related papers  (2026-03-17T03:43:37Z)
• EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding [66.80528512321106]
  EmbodiedSplat is an online feed-forward 3DGS for open-vocabulary scene understanding.<n>Our objectives are 1) Reconstructs the semantic-embedded 3DGS of the entire scene from over 300 streaming images in an online manner, and 2) Highly generalizable to novel scenes with feed-forward design.
  arXiv  Detail & Related papers  (2026-03-04T16:40:41Z)
• Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing [63.141976759536625]
  We propose Interp3D, a training-free framework for textured 3D morphing.<n>It harnesses generative priors and adopts a progressive alignment principle to ensure both geometric fidelity and texture coherence.<n>For comprehensive evaluations, we construct a dedicated dataset, Interp3DData, with graded difficulty levels and assess generation results from fidelity, transition smoothness, and plausibility.
  arXiv  Detail & Related papers  (2026-01-20T16:03:22Z)
• WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion [78.20778143251171]
  WorldWarp is a framework that couples a 3D structural anchor with a 2D generative refiner.<n>WorldWarp maintains consistency across video chunks by dynamically updating the 3D cache at every step.<n>It achieves state-of-the-art fidelity by ensuring that 3D logic guides structure while diffusion logic perfects texture.
  arXiv  Detail & Related papers  (2025-12-22T18:53:50Z)
• Vista3D: Unravel the 3D Darkside of a Single Image [64.00066024235088]
  Vista3D is a framework that realizes swift and consistent 3D generation within a mere 5 minutes. In the coarse phase, we rapidly generate initial geometry with Gaussian Splatting from a single image. It elevates the quality of generation by using a disentangled representation with two independent implicit functions.
  arXiv  Detail & Related papers  (2024-09-18T17:59:44Z)
• A3D: Does Diffusion Dream about 3D Alignment? [73.97853402817405]
  We tackle the problem of text-driven 3D generation from a geometry alignment perspective.<n>Given a set of text prompts, we aim to generate a collection of objects with semantically corresponding parts aligned across them.<n>We propose to embed these objects into a common latent space and optimize the continuous transitions between these objects.
  arXiv  Detail & Related papers  (2024-06-21T09:49:34Z)
• MetaDreamer: Efficient Text-to-3D Creation With Disentangling Geometry and Texture [1.5601951993287981]
  We introduce MetaDreammer, a two-stage optimization approach that leverages rich 2D and 3D prior knowledge. In the first stage, our emphasis is on optimizing the geometric representation to ensure multi-view consistency and accuracy of 3D objects. In the second stage, we concentrate on fine-tuning the geometry and optimizing the texture, thereby achieving a more refined 3D object.
  arXiv  Detail & Related papers  (2023-11-16T11:35:10Z)
• SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D [40.088688751115214]
  It is inherently ambiguous to lift 2D results from pre-trained diffusion models to a 3D world for text-to-3D generation. We improve consistency by aligning the 2D geometric priors in diffusion models with well-defined 3D shapes during the lifting. Our method represents a new state-of-the-art performance with an 85+% consistency rate by human evaluation.
  arXiv  Detail & Related papers  (2023-10-04T05:59:50Z)
• Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors [104.79392615848109]
  We present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes from a single unposed image. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture.
  arXiv  Detail & Related papers  (2023-06-30T17:59:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.