PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
October 8, 20250 citationsOpen Access

ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary

View Full Paper
ZGZeqi GuYCYin CuiZLZhaoshuo Li

Key Points

  • ArtiScene enhances layout and aesthetic quality in 3D scene generation through a two-step image processing method.
  • The approach integrates text-to-image generation with 3D modeling techniques, leading to superior performance in user satisfaction and quantitative metrics.
  • This innovative method requires no additional training, simplifying the 3D design process for users with varying expertise.
  • User studies show a 74.89% success rate, outperforming prior state-of-the-art approaches for scene generation.

Abstract

Designing 3D scenes is traditionally a challenging task that demands both artistic expertise and proficiency with complex software. Recent advances in text-to-3D generation have greatly simplified this process by letting users create scenes based on simple text descriptions. However, as these methods generally require extra training or in-context learning, their performance is often hindered by the limited availability of high-quality 3D data. In contrast, modern text-to-image models learned from web-scale images can generate scenes with diverse, reliable spatial layouts and consistent, visually appealing styles. Our key insight is that instead of learning directly from 3D scenes, we can leverage generated 2D images as an intermediary to guide 3D synthesis. In light of this, we introduce ArtiScene, a training-free automated pipeline for scene design that integrates the flexibility of free-form text-to-image generation with the diversity and reliability of 2D intermediary layouts. First, we generate 2D images from a scene description, then extract the shape and appearance of objects to create 3D models. These models are assembled into the final scene using geometry, position, and pose information derived from the same intermediary image. Being generalizable to a wide range of scenes and styles, ArtiScene outperforms state-of-the-art benchmarks by a large margin in layout and aesthetic quality by quantitative metrics. It also averages a 74.89% winning rate in extensive user studies and 95.07% in GPT-4o evaluation. Project page: https://artiscene-cvpr.github.io/

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Gu et al. (2025) studied this question.

synapsesocial.com/papers/68e6f342f8145af55aeacacbhttps://doi.org/10.48550/arxiv.2506.00742
Ask AI
Helpful
Bookmark
Share
View Full Paper