mlsanityData to 7 Oct 2026

3DStyleGLIP: Part-Tailored Text-Guided 3D Neural Stylization

arXiv 2404.02634 ↗First posted 3 Apr 2024cs.CV cs.GRcited by 4

Not on the map. Why?

Abstract (arXiv)

3D stylization, the application of specific styles to three-dimensional objects, offers substantial commercial potential by enabling the creation of uniquely styled 3D objects tailored to diverse scenes. Recent advancements in artificial intelligence and text-driven manipulation methods have made the stylization process increasingly intuitive and automated. While these methods reduce human costs by minimizing reliance on manual labor and expertise, they predominantly focus on holistic stylization, neglecting the application of desired styles to individual components of a 3D object. This limitation restricts the fine-grained controllability. To address this gap, we introduce 3DStyleGLIP, a novel framework specifically designed for text-driven, part-tailored 3D stylization. Given a 3D mesh and a text prompt, 3DStyleGLIP utilizes the vision-language embedding space of the Grounded Language-Image Pre-training (GLIP) model to localize individual parts of the 3D mesh and modify their appearance to match the styles specified in the text prompt. 3DStyleGLIP effectively integrates part localization and stylization guidance within GLIP's shared embedding space through an end-to-end process, enabled by part-level style loss and two complementary learning techniques. This neural methodology meets the user's need for fine-grained style editing and delivers high-quality part-specific stylization results, opening new possibilities for customization and flexibility in 3D content creation. Our code and results are available at https://github.com/sj978/3DStyleGLIP.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 48 of its 77 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

48 of 77 references.

References · 48

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  6. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  7. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  8. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  9. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  10. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  11. 2020Oscar: Object-Semantics Aligned Pre-training for Vision-Language Taskscited by 1,213
  12. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
36 more
  1. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 990
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  3. 2019VL-BERT: Pre-training of Generic Visual-Linguistic Representationscited by 954
  4. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  5. 2021MDETR -- Modulated Detection for End-to-End Multi-Modal Understandingcited by 811
  6. 2021Vector-quantized Image Modeling with Improved VQGANcited by 656
  7. 2021FLAVA: A Foundational Language And Vision Alignment Modelcited by 646
  8. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  9. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  10. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  11. 2017Neural 3D Mesh Renderercited by 437
  12. 2021VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Expertscited by 424
  13. 2023TEXTure: Text-Guided Texturing of 3D Shapescited by 303
  14. 2022CLIP-Mesh: Generating textured meshes from text using pretrained image-text modelscited by 281
  15. 2023Text2Tex: Text-driven Texture Synthesis via Diffusion Modelscited by 234
  16. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  17. 2021CLIPstyler: Image Style Transfer with a Single Text Conditioncited by 203
  18. 2020FCOS: A simple and strong anchor-free object detectorcited by 171
  19. 2022StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learningcited by 140
  20. 2023TextDeformer: Geometry Manipulation using Text Guidancecited by 94
  21. 2022TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decompositioncited by 83
  22. 2021CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directionscited by 78
  23. 2021Learning to Stylize Novel Viewscited by 76
  24. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  25. 2021StyleMesh: Style Transfer for Indoor 3D Scene Reconstructionscited by 58
  26. 2022UPST-NeRF: Universal Photorealistic Style Transfer of Neural Radiance Fields for 3D Scenecited by 47
  27. 2020Location-aware Single Image Reflection Removalcited by 43
  28. 2022Text and Image Guided 3D Avatar Generation and Manipulationcited by 35
  29. 20223D Highlighter: Localizing Regions on 3D Shapes via Text Descriptionscited by 32
  30. 2021Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIPcited by 21
  31. 2023Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Detailscited by 18
  32. 2022clip2latent: Text driven sampling of a pre-trained StyleGAN using denoising diffusion and CLIPcited by 16
  33. 2022Name Your Style: An Arbitrary Artist-aware Image Style Transfercited by 14
  34. 2020Lagrangian Neural Style Transfer for Fluidscited by 11
  35. 2019Transport-Based Neural Style Transfer for Smoke Simulationscited by 10
  36. 2023StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Modelcited by 10

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2024SAMPart3D: Segment Any Part in 3D Objectscited by 95
  2. 2025Voxify3D: Pixel Art Meets Volumetric Renderingcited by 3
  3. 2025CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answeringcited by 0
  4. 2025SplatFont3D: Structure-Aware Text-to-3D Artistic Font Generation with Part-Level Style Controlcited by 0