Research map / Image generation / Autoregressive and latent generation
D3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection
Yanran Zhang, Bingyao Yu, Yu Zheng, Wenzhao Zheng, Yueqi Duan, Lei Chen, Jie Zhou, Jiwen Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add VQVAE residual features to CLIP-only model (ablation) | D3QE · ARForensics | accuracy: 79.56 -> 79.92 | Improved |
| Use residual features instead of discrete z_q with vanilla transformer (ablation) | D3QE · ARForensics | accuracy: 80.39 -> 80.72 | Improved |
| Replace vanilla transformer with D3AT (ablation) | D3QE · ARForensics | accuracy: 80.72 -> 82.11 | Improved |
| Set D3AT dimension to 512 instead of 128 (ablation) | D3QE · ARForensics | accuracy: 80.83 -> 82.11 | Improved |
| Set D3AT dimension to 512 instead of 1024 (ablation) | D3QE · ARForensics | accuracy: 80.37 -> 82.11 | Improved |
| Use D3QE instead of CNNSpot | CNNSpot · ARForensics | mean accuracy: 64.90 -> 82.11 | Improved |
| Use D3QE instead of UnivFD on VAR | UnivFD · ARForensics VAR | accuracy: 80.53 -> 85.33 | Improved |
| Train on LlamaGen only, test on GANs: D3QE vs UnivFD | UnivFD · ForenSynths GANs | mean accuracy: 80.70 -> 83.73 | Improved |
| Train on LlamaGen only, test on diffusion: D3QE vs UnivFD | UnivFD · GenImage | mean accuracy: 78.42 -> 78.61 | No clear effect |
| Use D3QE instead of NPR | NPR · ARForensics Infinity | accuracy: 88.48 -> 62.88 | Hurt |
Later papers that compared with this method
1 later accepted paper reports D3QE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection (CVPR 2026 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation (ICLR 2025 · similarity 0.88)
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (NeurIPS 2024 · similarity 0.87)
- Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation (NeurIPS 2025 · similarity 0.86)
- Fundamental Limits of Visual Autoregressive Transformers: Universal Approximation Abilities (ICML 2025 · similarity 0.86)
- Autoregressive Image Generation without Vector Quantization (NeurIPS 2024 · similarity 0.86)
- Q-ARVD: Quantizing Autoregressive Video Diffusion Models (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
