SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation

• URL: http://arxiv.org/abs/2603.15150v1
• Date: Mon, 16 Mar 2026 11:44:11 GMT
• Title: SNCE: Geometry-Aware Supervision for Scalable Discrete Image Generation
• Abstract summary: Neighbor Cross Entropy Minimization (SNCE) is a novel training objective designed to address the optimization challenges of large-codebook discrete image generators.<n>We conduct experiments across class-conditional ImageNet-256 generation, large-scale text-to-image synthesis, and image editing tasks.<n>Results show that SNCE significantly improves convergence speed and overall generation quality compared to standard cross-entropy objectives.
• Score: 64.29376407025768
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advancements in discrete image generation showed that scaling the VQ codebook size significantly improves reconstruction fidelity. However, training generative models with a large VQ codebook remains challenging, typically requiring larger model size and a longer training schedule. In this work, we propose Stochastic Neighbor Cross Entropy Minimization (SNCE), a novel training objective designed to address the optimization challenges of large-codebook discrete image generators. Instead of supervising the model with a hard one-hot target, SNCE constructs a soft categorical distribution over a set of neighboring tokens. The probability assigned to each token is proportional to the proximity between its code embedding and the ground-truth image embedding, encouraging the model to capture semantically meaningful geometric structure in the quantized embedding space. We conduct extensive experiments across class-conditional ImageNet-256 generation, large-scale text-to-image synthesis, and image editing tasks. Results show that SNCE significantly improves convergence speed and overall generation quality compared to standard cross-entropy objectives.

Related papers

• Where Does Generative Difficulty Reside? An Empirical Study of Target Representations [62.54876287800644]
  The target representation defines the distribution an image generator must learn, yet it is often treated as an interchangeable interface.<n>We study raw pixels, SD-VAE latents and DINOv2 as well as MAE representation-autoencoder features within a unified masked autoregressive rectified-flow model.<n>Our results show that compression, reconstruction fidelity, token dimensionality, and visible semantic clustering do not individually predict generative behavior.
  arXiv  Detail & Related papers  (2026-08-01T12:32:31Z)
• GloTok: Global Perspective Tokenizer for Image Reconstruction and Generation [51.95701097588426]
  We introduce a Global Perspective Tokenizer (GloTok) to model a more uniform semantic distribution of tokenized features.<n>A residual learning module is proposed to recover the fine-grained details to minimize the reconstruction error caused by quantization.<n>Experiments on the standard ImageNet-1k benchmark clearly show that our proposed method achieves state-of-the-art reconstruction performance and generation quality.
  arXiv  Detail & Related papers  (2025-11-18T06:40:26Z)
• Boosting Generative Image Modeling via Joint Image-Feature Synthesis [15.133906625258797]
  We introduce a novel generative image modeling framework that seamlessly bridges the gap by leveraging a diffusion model to jointly model low-level image latents.<n>Our latent-semantic diffusion approach learns to generate coherent image-feature pairs from pure noise.<n>By eliminating the need for complex distillation objectives, our unified design simplifies training and unlocks a powerful new inference strategy: Representation Guidance.
  arXiv  Detail & Related papers  (2025-04-22T17:41:42Z)
• Frequency Autoregressive Image Generation with Continuous Tokens [31.833852108014312]
  We introduce the frequency progressive autoregressive (textbfFAR) paradigm and instantiate FAR with the continuous tokenizer.<n>We demonstrate the efficacy of FAR through comprehensive experiments on the ImageNet dataset.
  arXiv  Detail & Related papers  (2025-03-07T10:34:04Z)
• Factorized Visual Tokenization and Generation [37.56136469262736]
  We introduce Factorized Quantization (FQ), a novel approach that revitalizes VQ-based tokenizers by decomposing a large codebook into multiple independent sub-codebooks.<n>This factorization reduces the lookup complexity of large codebooks, enabling more efficient and scalable visual tokenization.<n> Experiments show that the proposed FQGAN model substantially improves the reconstruction quality of visual tokenizers, achieving state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-25T18:59:53Z)
• Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis [62.57727062920458]
  We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL.<n>We leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers.<n>Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images.
  arXiv  Detail & Related papers  (2024-10-10T17:59:17Z)
• Unlocking Pre-trained Image Backbones for Semantic Image Synthesis [29.688029979801577]
  We propose a new class of GAN discriminators for semantic image synthesis that generates highly realistic images. Our model, which we dub DP-SIMS, achieves state-of-the-art results in terms of image quality and consistency with the input label maps on ADE-20K, COCO-Stuff, and Cityscapes.
  arXiv  Detail & Related papers  (2023-12-20T09:39:19Z)
• Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation [78.13793505707952]
  Existing autoregressive models follow the two-stage generation paradigm that first learns a codebook in the latent space for image reconstruction and then completes the image generation autoregressively based on the learned codebook. We propose a novel two-stage framework, which consists of Masked Quantization VAE (MQ-VAE) Stack model from modeling redundancy.
  arXiv  Detail & Related papers  (2023-05-23T02:15:53Z)
• FewGAN: Generating from the Joint Distribution of a Few Images [95.6635227371479]
  We introduce FewGAN, a generative model for generating novel, high-quality and diverse images. FewGAN is a hierarchical patch-GAN that applies quantization at the first coarse scale, followed by a pyramid of residual fully convolutional GANs at finer scales. In an extensive set of experiments, it is shown that FewGAN outperforms baselines both quantitatively and qualitatively.
  arXiv  Detail & Related papers  (2022-07-18T07:11:28Z)
• InvGAN: Invertible GANs [88.58338626299837]
  InvGAN, short for Invertible GAN, successfully embeds real images to the latent space of a high quality generative model. This allows us to perform image inpainting, merging, and online data augmentation.
  arXiv  Detail & Related papers  (2021-12-08T21:39:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.