Syn3DTxt: Embedding 3D Cues for Scene Text Generation

• URL: http://arxiv.org/abs/2505.18479v1
• Date: Sat, 24 May 2025 02:53:24 GMT
• Title: Syn3DTxt: Embedding 3D Cues for Scene Text Generation
• Authors: Li-Syun Hsiung, Jun-Kai Tu, Kuan-Wu Chu, Yu-Hsuan Chiu, Yan-Tsung Peng, Sheng-Luen Chung, Gee-Sern Jison Hsu,
• Abstract summary: We investigate the challenge of insufficient three-dimensional context in synthetic datasets for scene text rendering.<n>Traditional 2D datasets do not provide the necessary geometric cues for accurately embedding text into diverse backgrounds.<n>We propose a novel standard for constructing synthetic datasets that incorporates surface normals to enrich three-dimensional scene characteristic.
• Score: 5.3618336695132625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This study aims to investigate the challenge of insufficient three-dimensional context in synthetic datasets for scene text rendering. Although recent advances in diffusion models and related techniques have improved certain aspects of scene text generation, most existing approaches continue to rely on 2D data, sourcing authentic training examples from movie posters and book covers, which limits their ability to capture the complex interactions among spatial layout and visual effects in real-world scenes. In particular, traditional 2D datasets do not provide the necessary geometric cues for accurately embedding text into diverse backgrounds. To address this limitation, we propose a novel standard for constructing synthetic datasets that incorporates surface normals to enrich three-dimensional scene characteristic. By adding surface normals to conventional 2D data, our approach aims to enhance the representation of spatial relationships and provide a more robust foundation for future scene text rendering methods. Extensive experiments demonstrate that datasets built under this new standard offer improved geometric context, facilitating further advancements in text rendering under complex 3D-spatial conditions.

Related papers

• MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation [19.46962637673285]
  MV-CoLight is a framework for illumination-consistent object compositing in 2D and 3D scenes.<n>We employ a Hilbert curve-based mapping to align 2D image inputs with 3D Gaussian scene representations seamlessly.<n> Experiments demonstrate state-of-the-art harmonized results across standard benchmarks and our dataset.
  arXiv  Detail & Related papers  (2025-05-27T17:53:02Z)
• Text To 3D Object Generation For Scalable Room Assembly [9.275648239993703]
  We propose an end-to-end system for synthetic data generation for scalable, high-quality, and customizable 3D indoor scenes.<n>This system generates highfidelity 3D object assets from text prompts and incorporates them into pre-defined floor plans using a rendering tool.
  arXiv  Detail & Related papers  (2025-04-12T20:13:07Z)
• Textured Mesh Saliency: Bridging Geometry and Texture for Human Perception in 3D Graphics [50.23625950905638]
  We present a new dataset for textured mesh saliency, created through an innovative eye-tracking experiment in a six degrees of freedom (6-DOF) VR environment.<n>Our proposed model predicts saliency maps for textured mesh surfaces by treating each triangular face as an individual unit and assigning a saliency density value to reflect the importance of each local surface region.
  arXiv  Detail & Related papers  (2024-12-11T08:27:33Z)
• DreamPolish: Domain Score Distillation With Progressive Geometry Generation [66.94803919328815]
  We introduce DreamPolish, a text-to-3D generation model that excels in producing refined geometry and high-quality textures. In the geometry construction phase, our approach leverages multiple neural representations to enhance the stability of the synthesis process. In the texture generation phase, we introduce a novel score distillation objective, namely domain score distillation (DSD), to guide neural representations toward such a domain.
  arXiv  Detail & Related papers  (2024-11-03T15:15:01Z)
• Semantic Score Distillation Sampling for Compositional Text-to-3D Generation [28.88237230872795]
  Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. We introduce a novel SDS approach, designed to improve the expressiveness and accuracy of compositional text-to-3D generation. Our approach integrates new semantic embeddings that maintain consistency across different rendering views. By leveraging explicit semantic guidance, our method unlocks the compositional capabilities of existing pre-trained diffusion models.
  arXiv  Detail & Related papers  (2024-10-11T17:26:00Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• InterFusion: Text-Driven Generation of 3D Human-Object Interaction [38.380079482331745]
  We tackle the complex task of generating 3D human-object interactions (HOI) from textual descriptions in a zero-shot text-to-3D manner. We present InterFusion, a two-stage framework specifically designed for HOI generation. Our experimental results affirm that InterFusion significantly outperforms existing state-of-the-art methods in 3D HOI generation.
  arXiv  Detail & Related papers  (2024-03-22T20:49:26Z)
• SceneWiz3D: Towards Text-guided 3D Scene Composition [134.71933134180782]
  Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. We introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text.
  arXiv  Detail & Related papers  (2023-12-13T18:59:30Z)
• CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion [83.30168660888913]
  We present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model.
  arXiv  Detail & Related papers  (2023-05-25T17:39:13Z)
• Compositional 3D Scene Generation using Locally Conditioned Diffusion [49.5784841881488]
  We introduce textbflocally conditioned diffusion as an approach to compositional scene diffusion. We demonstrate a score distillation sampling--based text-to-3D synthesis pipeline that enables compositional 3D scene generation at a higher fidelity than relevant baselines.
  arXiv  Detail & Related papers  (2023-03-21T22:37:16Z)
• A Scene-Text Synthesis Engine Achieved Through Learning from Decomposed Real-World Data [4.096453902709292]
  Scene-text image synthesis techniques aim to naturally compose text instances on background scene images. We propose a Learning-Based Text Synthesis engine (LBTS) that includes a text location proposal network (TLPNet) and a text appearance adaptation network (TAANet) After training, those networks can be integrated and utilized to generate the synthetic dataset for scene text analysis tasks.
  arXiv  Detail & Related papers  (2022-09-06T11:15:58Z)

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.