Research map / Image generation / Autoregressive and latent generation
Next Visual Granularity Generation
Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy
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 |
|---|---|---|---|
| replace VAR with NVG visual granularity generation | VAR · ImageNet 256 (d16) | FID: 3.30 -> 3.03 | Improved |
| replace VAR with NVG | VAR · ImageNet 256 (d20) | FID: 2.57 -> 2.44 | Improved |
| replace VAR with NVG | VAR · ImageNet 256 (d24) | FID: 2.09 -> 2.06 | No clear effect |
| scale NVG from d16 to d24 | NVG · ImageNet 256 | FID: 3.03 -> 2.44 -> 2.06 | Improved |
| use NVG granularity tokenizer instead of VAR's | VAR tokenizer · ImageNet val reconstruction | rFID: 1.06 -> 0.74 | Improved |
| add partial-noise (inpainting) structure input vs pure noise (ablation) | NVG-d12 · ImageNet ablation | FID: 37.89 -> 37.59 | Improved |
| add structure-aware RoPE (ablation) | NVG-d12 · ImageNet ablation | FID: 39.03 -> 37.59 | Improved |
| add noise to content input canvas (ablation) | NVG-d12 · ImageNet ablation | FID: 37.89 -> 38.94 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RandAR-XXL — RandAR: Decoder-only Autoregressive Visual Generation in Random Orders (CVPR 2025) · 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
- TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation (NeurIPS 2025 · similarity 0.87)
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction (NeurIPS 2024 · similarity 0.86)
- Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction (CVPR 2025 · similarity 0.85)
- Image Understanding Makes for A Good Tokenizer for Image Generation (NeurIPS 2024 · similarity 0.85)
- Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis (CVPR 2025 · similarity 0.85)
- When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization (NeurIPS 2025 · similarity 0.85)
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.
