mlsanityData to 7 Oct 2026

Pomo3D: 3D-Aware Portrait Accessorizing and More

arXiv 2409.14430 ↗First posted 22 Sep 2024cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose Pomo3D, a 3D portrait manipulation framework that allows free accessorizing by decomposing and recomposing portraits and accessories. It enables the avatars to attain out-of-distribution (OOD) appearances of simultaneously wearing multiple accessories. Existing methods still struggle to offer such explicit and fine-grained editing; they either fail to generate additional objects on given portraits or cause alterations to portraits (e.g., identity shift) when generating accessories. This restriction presents a noteworthy obstacle as people typically seek to create charming appearances with diverse and fashionable accessories in the virtual universe. Our approach provides an effective solution to this less-addressed issue. We further introduce the Scribble2Accessories module, enabling Pomo3D to create 3D accessories from user-drawn accessory scribble maps. Moreover, we design a bias-conscious mapper to mitigate biased associations present in real-world datasets. In addition to object-level manipulation above, Pomo3D also offers extensive editing options on portraits, including global or local editing of geometry and texture and avatar stylization, elevating 3D editing of neural portraits to a more comprehensive level.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 67 of its 82 references that are in the map. First posted on arXiv 22 Sep 2024.

Builds on

67 of 82 references.

References · 67

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2017Neural Discrete Representation Learningcited by 4,650
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  9. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  10. 2018Demystifying MMD GANscited by 1,268
  11. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  12. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
38 more
  1. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  2. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  3. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  4. 2020Convolutional Occupancy Networkscited by 760
  5. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  6. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  7. 2018Which Training Methods for GANs do actually Converge?cited by 672
  8. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  9. 2019MaskGAN: Towards Diverse and Interactive Facial Image Manipulationcited by 624
  10. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  11. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 465
  12. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  13. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  14. 2021Advances in Neural Renderingcited by 365
  15. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  16. 2020StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flowscited by 348
  17. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  18. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  19. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  20. 2020StyleRig: Rigging StyleGAN for 3D Control over Portrait Imagescited by 267
  21. 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
  22. 2020Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learningcited by 219
  23. 2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
  24. 2021CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesiscited by 149
  25. 2022Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatarscited by 124
  26. 2021FENeRF: Face Editing in Neural Radiance Fieldscited by 112
  27. 20213D-aware Image Synthesis via Learning Structural and Textural Representationscited by 109
  28. 2022GIRAFFE HD: A High-Resolution 3D-aware Generative Modelcited by 86
  29. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  30. 2022Pix2NeRF: Unsupervised Conditional π-GAN for Single Image to Neural Radiance Fields Translationcited by 73
  31. 2020SofGAN: A Portrait Image Generator with Dynamic Stylingcited by 65
  32. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  33. 2024Advances in 3D Generation: A Surveycited by 62
  34. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  35. 2023DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatarscited by 42
  36. 2022Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Imagescited by 39
  37. 2022NeRFFaceEditing: Disentangled Face Editing in Neural Radiance Fieldscited by 33
  38. 2023HoloFusion: Towards Photo-realistic 3D Generative Modelingcited by 32

50 most cited of 67 All 67 (JSON)

Built on by

Not cited yet.