mlsanityData to 7 Oct 2026

Adversarial Score Distillation: When score distillation meets GAN

arXiv 2312.00739 ↗First posted 1 Dec 2023cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Existing score distillation methods are sensitive to classifier-free guidance (CFG) scale: manifested as over-smoothness or instability at small CFG scales, while over-saturation at large ones. To explain and analyze these issues, we revisit the derivation of Score Distillation Sampling (SDS) and decipher existing score distillation with the Wasserstein Generative Adversarial Network (WGAN) paradigm. With the WGAN paradigm, we find that existing score distillation either employs a fixed sub-optimal discriminator or conducts incomplete discriminator optimization, resulting in the scale-sensitive issue. We propose the Adversarial Score Distillation (ASD), which maintains an optimizable discriminator and updates it using the complete optimization objective. Experiments show that the proposed ASD performs favorably in 2D distillation and text-to-3D tasks against existing methods. Furthermore, to explore the generalization ability of our WGAN paradigm, we extend ASD to the image editing task, which achieves competitive results. The project page and code are at https://github.com/2y7c3/ASD.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 49 of its 64 references that are in the map. First posted on arXiv 1 Dec 2023.

Builds on

49 of 64 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2022Classifier-Free Diffusion Guidancecited by 5,717
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  8. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  10. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  11. 2017Improved Training of Wasserstein GANscited by 2,223
  12. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
37 more
  1. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  2. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  3. 2016Least Squares Generative Adversarial Networkscited by 1,000
  4. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  5. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 886
  6. 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
  7. 2023Adversarial Diffusion Distillationcited by 741
  8. 2021GPT Understands, Toocited by 715
  9. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  10. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  11. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  12. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  13. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  14. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  15. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  16. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  17. 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
  18. 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
  19. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
  20. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 232
  21. 2023Re-imagine the Negative Prompt Algorithm: Transform 2D Diffusion into 3D, alleviate Janus problem and Beyondcited by 139
  22. 2022KronA: Parameter Efficient Tuning with Kronecker Adaptercited by 130
  23. 2023Text-to-3D with Classifier Score Distillationcited by 127
  24. 2016Neural Photo Editing with Introspective Adversarial Networkscited by 109
  25. 2020A Survey on Generative Adversarial Networks: Variants, Applications, and Trainingcited by 97
  26. 2018Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Languagecited by 90
  27. 2017Improved Adversarial Systems for 3D Object Generation and Reconstructioncited by 66
  28. 2023IT3D: Improved Text-to-3D Generation with Explicit View Synthesiscited by 63
  29. 2017Perceptual Adversarial Networks for Image-to-Image Transformationcited by 42
  30. 2023Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generationcited by 39
  31. 2022Diffusion Guided Domain Adaptation of Image Generatorscited by 35
  32. 2021Wasserstein GANs Work Because They Fail (to Approximate the Wasserstein Distance)cited by 33
  33. 20173D Object Reconstruction from a Single Depth View with Adversarial Learningcited by 26
  34. 2023Collaborative Score Distillation for Consistent Visual Synthesiscited by 23
  35. 2017Wasserstein Divergence for GANscited by 22
  36. 2017Eye In-Painting with Exemplar Generative Adversarial Networkscited by 18
  37. 2019How Well Do WGANs Estimate the Wasserstein Metric?cited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024DreamReward: Text-to-3D Generation with Human Preferencecited by 56
  2. 2025Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistencycited by 34
  3. 2025Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Controlcited by 14
  4. 2025MixerMDM: Learnable Composition of Human Motion Diffusion Modelscited by 13
  5. 2025Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Datacited by 7
  6. 2025Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generationcited by 6
  7. 2024DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mappingcited by 5
  8. 2026ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuningcited by 5
  9. 2025VDOT: Efficient Unified Video Creation via Optimal Transport Distillationcited by 4
  10. 2025Walking the Schr"odinger Bridge: A Direct Trajectory for Text-to-3D Generationcited by 3
  11. 2026AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Losscited by 3
  12. 2025Text-to-3D Generation using Jensen-Shannon Score Distillationcited by 2
3 more
  1. 2025Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infillingcited by 2
  2. 2024Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillationcited by 1
  3. 2025Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillationcited by 0