mlsanityData to 14 Oct 2026

LADIS: Language Disentanglement for 3D Shape Editing

arXiv 2212.05011 ↗First posted 9 Dec 2022cs.CV cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Natural language interaction is a promising direction for democratizing 3D shape design. However, existing methods for text-driven 3D shape editing face challenges in producing decoupled, local edits to 3D shapes. We address this problem by learning disentangled latent representations that ground language in 3D geometry. To this end, we propose a complementary tool set including a novel network architecture, a disentanglement loss, and a new editing procedure. Additionally, to measure edit locality, we define a new metric that we call part-wise edit precision. We show that our method outperforms existing SOTA methods by 20% in terms of edit locality, and up to 6.6% in terms of language reference resolution accuracy. Our work suggests that by solely disentangling language representations, downstream 3D shape editing can become more local to relevant parts, even if the model was never given explicit part-based supervision.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 26 of its 43 references that are in the map. First posted on arXiv 9 Dec 2022.

Builds on

26 of 43 references.

References · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  5. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  6. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  7. 2021StyleCLIP: Text-Driven Manipulation of StyleGAN Imagerycited by 991
  8. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  9. 2018Disentangling by Factorisingcited by 616
  10. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  11. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  12. 2019ScanRefer: 3D Object Localization in RGB-D Scans using Natural Languagecited by 452
14 more
  1. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
  2. 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 334
  3. 2020Learning Gradient Fields for Shape Generationcited by 245
  4. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 241
  5. 2018Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddingscited by 169
  6. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  7. 2018Structured Disentangled Representationscited by 62
  8. 2019ShapeGlot: Learning Language for Shape Differentiationcited by 54
  9. 2021Language Grounding with 3D Objectscited by 43
  10. 2021DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinatescited by 37
  11. 2019Geometric Disentanglement for Generative Latent Shape Modelscited by 30
  12. 2021PartGlot: Learning Shape Part Segmentation from Language Reference Gamescited by 30
  13. 2019StructEdit: Learning Structural Shape Variationscited by 23
  14. 2018Auto-Encoding Total Correlation Explanationcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 1; 2025: 0; 2026: 2.

10 papers.

  1. 2023Vox-E: Text-guided Voxel Editing of 3D Objectscited by 115
  2. 2023Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Taskcited by 93
  3. 2022ScanEnts3D: Exploiting Phrase-to-3D-Object Correspondences for Improved Visio-Linguistic Models in 3D Scenescited by 32
  4. 2023Parts of Speech-Grounded Subspaces in Vision-Language Modelscited by 11
  5. 2023Aladdin: Zero-Shot Hallucination of Stylized 3D Assets from Abstract Scene Descriptionscited by 11
  6. 2023CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Explorationcited by 9
  7. 2024CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimizationcited by 8
  8. 2023Spice-E : Structural Priors in 3D Diffusion using Cross-Entity Attentioncited by 7
  9. 20263DMorph: Single-Image-Guided Local 3D Shape Editing and Morphingcited by 0
  10. 2026CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representationcited by 0