# Adversarial Score Distillation: When score distillation meets GAN

arXiv: https://arxiv.org/abs/2312.00739 · HTML: https://mlsanity.com/paper/2312.00739/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 64 references that are in the map.
- First posted on arXiv 1 Dec 2023.

## Builds on (most cited first, 30 of 49)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [MVDream: Multi-view Diffusion for 3D Generation](https://mlsanity.com/paper/2308.16512/) (2023)
- [Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning](https://mlsanity.com/paper/2205.05638/) (2022)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Adversarial Diffusion Distillation](https://mlsanity.com/paper/2311.17042/) (2023)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures](https://mlsanity.com/paper/2211.07600/) (2022)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Generative Visual Manipulation on the Natural Image Manifold](https://mlsanity.com/paper/1609.03552/) (2016)
- [Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1808.00948/) (2018)
- [Learning to Discover Cross-Domain Relations with Generative Adversarial Networks](https://mlsanity.com/paper/1703.05192/) (2017)

## Built on by (most cited first, 15 of 15)

- [DreamReward: Text-to-3D Generation with Human Preference](https://mlsanity.com/paper/2403.14613/) (2024)
- [Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency](https://mlsanity.com/paper/2503.20785/) (2025)
- [Taming Video Models for 3D and 4D Generation via Zero-Shot Camera Control](https://mlsanity.com/paper/2509.15130/) (2025)
- [MixerMDM: Learnable Composition of Human Motion Diffusion Models](https://mlsanity.com/paper/2504.01019/) (2025)
- [Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data](https://mlsanity.com/paper/2503.21694/) (2025)
- [Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation](https://mlsanity.com/paper/2509.15772/) (2025)
- [ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning](https://mlsanity.com/paper/2602.03425/) (2026)
- [DreamMapping: High-Fidelity Text-to-3D Generation via Variational Distribution Mapping](https://mlsanity.com/paper/2409.05099/) (2024)
- [VDOT: Efficient Unified Video Creation via Optimal Transport Distillation](https://mlsanity.com/paper/2512.06802/) (2025)
- [AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss](https://mlsanity.com/paper/2608.11205/) (2026)
- [Walking the Schr"odinger Bridge: A Direct Trajectory for Text-to-3D Generation](https://mlsanity.com/paper/2511.05609/) (2025)
- [Text-to-3D Generation using Jensen-Shannon Score Distillation](https://mlsanity.com/paper/2503.10660/) (2025)
- [Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling](https://mlsanity.com/paper/2510.23605/) (2025)
- [Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation](https://mlsanity.com/paper/2408.15991/) (2024)
- [Advancing Text-to-3D Generation with Linearized Lookahead Variational Score Distillation](https://mlsanity.com/paper/2507.09748/) (2025)

## 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.