mlsanityData to 14 Oct 2026

PixNerd: Pixel Neural Field Diffusion

arXiv 2507.23268 ↗First posted 31 Jul 2025cs.CVcited by 82

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The current success of diffusion transformers heavily depends on the compressed latent space shaped by the pre-trained variational autoencoder(VAE). However, this two-stage training paradigm inevitably introduces accumulated errors and decoding artifacts. To address the aforementioned problems, researchers return to pixel space at the cost of complicated cascade pipelines and increased token complexity. In contrast to their efforts, we propose to model the patch-wise decoding with neural field and present a single-scale, single-stage, efficient, end-to-end solution, coined as pixel neural field diffusion~(PixelNerd). Thanks to the efficient neural field representation in PixNerd, we directly achieved 2.15 FID on ImageNet 256×256 and 2.84 FID on ImageNet 512×512 without any complex cascade pipeline or VAE. We also extend our PixNerd framework to text-to-image applications. Our PixNerd-XXL/16 achieved a competitive 0.73 overall score on the GenEval benchmark and 80.9 overall score on the DPG benchmark.

Key facts. Cited by 82 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 71 of its 77 references that are in the map. First posted on arXiv 31 Jul 2025.

Builds on

71 of 77 references.

Closest ancestors · 27

Same direction, newest first

  1. 2025REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers14 Apr
  2. 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models2 Jan
  3. 2024Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models14 Oct
  4. 2024Diffusion Models Need Visual Priors for Image Generation11 Oct
  5. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think9 Oct
  6. 2024Efficient Training with Denoised Neural Weights16 Jul
  7. 2024Image Neural Field Diffusion Models11 Jun
  8. 2024Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis21 Apr
  9. 2024Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models11 Apr
  10. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation5 Apr
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesis5 Mar
  12. 2024FiT: Flexible Vision Transformer for Diffusion Model19 Feb
15 more
  1. 2024DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations23 Jan
  2. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers16 Jan
  3. 2023Analyzing and Improving the Training Dynamics of Diffusion Models5 Dec
  4. 2023Relay Diffusion: Unifying diffusion process across resolutions for image synthesis4 Sep
  5. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models25 Apr
  6. 2023Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation1 Mar
  7. 2023Simple diffusion: End-to-end diffusion for high resolution images26 Jan
  8. 2022Scalable Diffusion Models with Transformers19 Dec
  9. 2022All are Worth Words: A ViT Backbone for Diffusion Models25 Sep
  10. 2022Classifier-Free Diffusion Guidance26 Jul
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  12. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  13. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  14. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  15. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 44

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  5. 2023Segment Anythingcited by 8,234
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  9. 2016Improved Techniques for Training GANscited by 2,970
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  11. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  12. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
32 more
  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  2. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  3. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  4. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 944
  5. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  6. 2024Autoregressive Image Generation without Vector Quantizationcited by 651
  7. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 492
  8. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 483
  9. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  10. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  11. 2025BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Datasetcited by 376
  12. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
  13. 2021Generating Images with Sparse Representationscited by 266
  14. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 205
  15. 2022Scalable Adaptive Computation for Iterative Generationcited by 195
  16. 2025Seedream 3.0 Technical Reportcited by 154
  17. 2024Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokenscited by 147
  18. 2020Adversarial Generation of Continuous Imagescited by 135
  19. 2025Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generationcited by 109
  20. 2025PixelFlow: Pixel-Space Generative Models with Flowcited by 97
  21. 2024Normalizing Flows are Capable Generative Modelscited by 91
  22. 2025SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RLcited by 86
  23. 2024DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesiscited by 72
  24. 2019COCO-GAN: Generation by Parts via Conditional Coordinatingcited by 67
  25. 2025Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Modelcited by 62
  26. 2024JetFormer: An Autoregressive Generative Model of Raw Images and Textcited by 46
  27. 2025Fractal Generative Modelscited by 46
  28. 2024Causal Diffusion Transformers for Generative Modelingcited by 31
  29. 2022Arbitrary-Scale Image Synthesiscited by 20
  30. 2025Native-Resolution Image Synthesiscited by 15
  31. 2025DMM: Building a Versatile Image Generation Model via Distillation-Based Model Mergingcited by 5
  32. 2024INRFlow: Flow Matching for INRs in Ambient Spacecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 17; 2026: 65.

82 papers.

Sort:

By area:

  1. 2025Diffusion Transformers with Representation Autoencoderscited by 295
  2. 2025What matters for Representation Alignment: Global Information or Spatial Structure?cited by 84
  3. 2025PixelDiT: Pixel Diffusion Transformers for Image Generationcited by 83
  4. 2025DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generationcited by 60
  5. 2026One-step Latent-free Image Generation with Pixel Mean Flowscited by 53
  6. 2025DiP: Taming Diffusion Models in Pixel Spacecited by 48
  7. 2026Representation Fr'echet Loss for Visual Generationcited by 37
  8. 2025FARMER: Flow AutoRegressive Transformer over Pixelscited by 18
  9. 2025Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusioncited by 18
  10. 2026Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generationcited by 18
  11. 2025Guiding a Diffusion Transformer with the Internal Dynamics of Itselfcited by 16
  12. 2026PixelGen: Improving Pixel Diffusion with Perceptual Supervisioncited by 14
38 more
  1. 2026Representation Alignment for Just Image Transformers is not Easier than You Thinkcited by 14
  2. 2026Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoderscited by 13
  3. 2025CoD: A Diffusion Foundation Model for Image Compressioncited by 10
  4. 2026L2P: Unlocking Latent Potential for Pixel Generationcited by 9
  5. 2026HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusioncited by 9
  6. 2026Asymmetric Flow Modelscited by 8
  7. 2026PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusioncited by 8
  8. 2025SimFlow: Simplified and End-to-End Training of Latent Normalizing Flowscited by 7
  9. 2026Revisiting Diffusion Model Predictions Through Dimensionalitycited by 7
  10. 2026CoD-Lite: Real-Time Diffusion-Based Generative Image Compressioncited by 7
  11. 2025Trainable Log-linear Sparse Attention for Efficient Diffusion Transformerscited by 6
  12. 2026End-to-End Training for Unified Tokenization and Latent Denoisingcited by 6
  13. 2026An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Modelscited by 6
  14. 2026Spectrally-Guided Diffusion Noise Schedulescited by 5
  15. 2026Continuous Adversarial Flow Modelscited by 5
  16. 2025RecTok: Reconstruction Distillation along Rectified Flowcited by 4
  17. 2026FrequencyBooster: Full-Frequency Modeling for High-Fidelity Pixel Diffusioncited by 4
  18. 2026Representation Forcing for Bottleneck-Free Unified Multimodal Modelscited by 4
  19. 2026UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformercited by 4
  20. 2026PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Spacecited by 4
  21. 2026Adaptive 1D Video Diffusion Autoencodercited by 3
  22. 2026Normalizing Flows with Iterative Denoisingcited by 3
  23. 2026FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generationcited by 3
  24. 2026WaiT for the Signal: Simple Frequency-Aware Flow-Matchingcited by 3
  25. 2025AutoPR: Let's Automate Your Academic Promotion!cited by 2
  26. 2026V-Co: A Closer Look at Visual Representation Alignment via Co-Denoisingcited by 2
  27. 2026Registers Matter for Pixel-Space Diffusion Transformerscited by 2
  28. 2026WavFlow: Audio Generation in Waveform Spacecited by 2
  29. 2026RiT: Vanilla Diffusion Transformers Suffice in Representation Spacecited by 2
  30. 2026Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusioncited by 2
  31. 2026Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectoriescited by 2
  32. 2026SPEED: One-Step Pixel Diffusion for High-quality Video Frame Interpolationcited by 2
  33. 2026Amortized Moment Matching for Visual Generationcited by 2
  34. 2026GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modelingcited by 2
  35. 2026Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusioncited by 2
  36. 2025Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaborationcited by 1
  37. 2025RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Modelcited by 1
  38. 2025MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixturecited by 1

50 most cited of 82 All 82 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
  2. 2026Advanced Pixel Diffusion Model with Guided Sparse Global Refinement
  3. 2024Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion
  4. 2024Pixel-Space Post-Training of Latent Diffusion Models
  5. 2025Toward Lightweight and Fast Decoders for Diffusion Models in Image and Video Generation
  6. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
  7. 2026PixSDS: Why Latent SDS Makes Noisy Pixels
  8. 2026PixRestore: Unified Image Restoration via Pixel Diffusion Transformer