mlsanityData to 7 Oct 2026

Sphere Encoder 2

arXiv 2610.02208 ↗First posted 1 Oct 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Sphere Encoder is an autoencoder that generates images by decoding random points from a high-dimensional latent sphere. We identify two limitations of the original formulation that reduce its generation quality. First, random points concentrate near the equator relative to the pole on an encoded latent, but the training rotation never reaches this region, leaving a gap that limits one-step generation. Second, training for generation with pixel-wise reconstruction loss encourages the decoder to average over plausible images, producing blurry images that lack high-frequency details. We present Sphere Encoder 2 to address both limitations, substantially improving image generation quality while maintaining the speed and simplicity of a autoencoder. Models are released at https://github.com/kaiyuyue/sphere2.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 77 of its 87 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

77 of 87 references.

References · 77

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  9. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  10. 2022Scalable Diffusion Models with Transformerscited by 5,931
  11. 2022Classifier-Free Diffusion Guidancecited by 5,717
  12. 2022Generative Adversarial Networkscited by 5,603
38 more
  1. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  3. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  4. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  7. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  8. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  9. 2023Consistency Modelscited by 1,778
  10. 2025DINOv3cited by 1,297
  11. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  12. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  13. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  14. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
  15. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  16. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  17. 2023Adversarial Diffusion Distillationcited by 741
  18. 2016Generative Adversarial Text to Image Synthesiscited by 735
  19. 2022On Distillation of Guided Diffusion Modelscited by 721
  20. 2024SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformerscited by 707
  21. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  22. 2024Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Thinkcited by 666
  23. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  24. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  25. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  26. 2025Mean Flows for One-step Generative Modelingcited by 524
  27. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  28. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  29. 2023Improved Techniques for Training Consistency Modelscited by 430
  30. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  31. 2025Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Modelscited by 376
  32. 2024One Step Diffusion via Shortcut Modelscited by 373
  33. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  34. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speedcited by 344
  35. 2024Guiding a Diffusion Model with a Bad Version of Itselfcited by 286
  36. 2024Simplifying, Stabilizing and Scaling Continuous-Time Consistency Modelscited by 276
  37. 2025Diffusion Transformers with Representation Autoencoderscited by 275
  38. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261

50 most cited of 77 All 77 (JSON)

Built on by

Not cited yet.