mlsanityData to 14 Oct 2026

Next Visual Granularity Generation

arXiv 2508.12811 ↗First posted 18 Aug 2025cs.CV cs.AI cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

We propose a novel approach to image generation by decomposing an image into a structured sequence, where each element in the sequence shares the same spatial resolution but differs in the number of unique tokens used, capturing different level of visual granularity. Image generation is carried out through our newly introduced Next Visual Granularity (NVG) generation framework, which generates a visual granularity sequence beginning from an empty image and progressively refines it, from global layout to fine details, in a structured manner. This iterative process encodes a hierarchical, layered representation that offers fine-grained control over the generation process across multiple granularity levels. We train a series of NVG models for class-conditional image generation on the ImageNet dataset and observe clear scaling behavior. Compared to the VAR series, NVG consistently outperforms it in terms of FID scores (3.30 rightarrow 3.03, 2.57 rightarrow 2.44, 2.09 rightarrow 2.06). We also conduct extensive analysis to showcase the capability and potential of the NVG framework. Our code and models are released at https://yikai-wang.github.io/nvg.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 46 of its 64 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

46 of 64 references.

References · 46

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2022Scalable Diffusion Models with Transformerscited by 6,054
  9. 2022Flow Matching for Generative Modelingcited by 5,702
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  11. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
34 more
  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  2. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  3. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  4. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  5. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  6. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  7. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,163
  8. 2022MaskGIT: Masked Generative Image Transformercited by 1,099
  9. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  10. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  11. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 737
  12. 2024MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategiescited by 723
  13. 2022Autoregressive Image Generation using Residual Quantizationcited by 722
  14. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 703
  15. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 694
  16. 2021Vector-quantized Image Modeling with Improved VQGANcited by 658
  17. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
  18. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  19. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  20. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  21. 2024An Image is Worth 32 Tokens for Reconstruction and Generationcited by 302
  22. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 211
  23. 2024Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generationcited by 155
  24. 2024Randomized Autoregressive Visual Generationcited by 127
  25. 2025FlexTok: Resampling Images into 1D Token Sequences of Flexible Lengthcited by 110
  26. 2024RandAR: Decoder-only Autoregressive Visual Generation in Random Orderscited by 83
  27. 2025Fractal Generative Modelscited by 46
  28. 2024DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generationcited by 32
  29. 2024Causal Diffusion Transformers for Generative Modelingcited by 31
  30. 2025Frequency Autoregressive Image Generation with Continuous Tokenscited by 27
  31. 2024Customize Your Visual Autoregressive Recipe with Set Autoregressive Modelingcited by 22
  32. 2025Spatial Reasoning with Denoising Modelscited by 16
  33. 2025Continuous Visual Autoregressive Generation via Score Maximizationcited by 9
  34. 2025D-AR: Diffusion via Autoregressive Modelscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencodingcited by 22
  2. 2026Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectoriescited by 2
  3. 2026Aligned Stable Inpainting: Mitigating Unwanted Object Insertion and Preserving Color Consistencycited by 0
  4. 2026Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioningcited by 0
  5. 2026QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generationcited by 0