Efficient Image Synthesis with Sphere Latent Encoder

• URL: http://arxiv.org/abs/2605.15592v1
• Date: Fri, 15 May 2026 04:03:06 GMT
• Title: Efficient Image Synthesis with Sphere Latent Encoder
• Abstract summary: Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps.<n> Sphere is a recent alternative that produces high-quality images in only a few steps.<n>We decouple the framework into a fixed pretrained image encoder and a separate latent denoising model trained entirely in a spherical latent space.<n>On Animal-Faces, Oxford-Flowers and ImageNet-1K datasets, our method significantly outperforms Sphere in both generation quality and inference speed.
• Score: 9.381297061959112
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Few-step image generation has seen rapid progress, with consistency and meanflow-based methods significantly reducing the number of sampling steps. Despite their low inference cost, these approaches often suffer from training instability and limited scalability. Sphere Encoder is a recent alternative that produces high-quality images in only a few steps; however, it requires repeated transitions between the pixel space and latent space during inference while jointly optimizing reconstruction and generation within a single architecture. This design leads to computational inefficiency and objective conflict between reconstruction and generation. To address these limitations, we decouple the framework into a fixed pretrained image encoder and a separate latent denoising model trained entirely in a spherical latent space. Our approach eliminates repeated pixel-space operations during training and inference, improving efficiency and allowing reconstruction and generation to specialize independently. On Animal-Faces, Oxford-Flowers and ImageNet-1K datasets, our method significantly outperforms Sphere Encoder in both generation quality and inference speed, while achieving competitive results against strong few-step and multi-step baselines.

Related papers

• Bridging Event Streams and DiT: Event-Guided Video Frame Interpolation [75.95737622994548]
  Event cameras provide high-resolution motion cues that are well suited for bridging temporal gaps.<n>We propose an adapter-based framework that incorporates event-derived cues into a pre-trained image-to-video diffusion model.
  arXiv  Detail & Related papers  (2026-08-11T04:47:44Z)
• Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation [9.199518837644424]
  Diffusion-based decoders have been adopted in image tokenization to reconstruct images from latent representations with high fidelity.<n>We introduce a two-stage acceleration framework to address this inefficiency.<n>We distill the diffusion decoder at each scale into a single-step denoising model, enabling fast and high-quality reconstructions.
  arXiv  Detail & Related papers  (2026-03-20T02:24:58Z)
• Image Generation with a Sphere Encoder [52.086777706390706]
  Sphere is an efficient generative framework capable of producing images in a single forward pass.<n>Our approach works by learning an encoder that maps uniformly onto a spherical latent space, and a decoder that maps random latent vectors back to the image space.
  arXiv  Detail & Related papers  (2026-02-16T18:59:57Z)
• Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation [36.41177812868683]
  Latent diffusion models excel at generating high-quality images but lose the benefits of end-to-end modeling.<n>We propose Latent Forcing, a simple modification to existing architectures that achieves the efficiency of latent diffusion while operating on raw natural images.<n>Latent Forcing achieves a new state-of-the-art for diffusion transformer-based pixel generation at our compute scale.
  arXiv  Detail & Related papers  (2026-02-11T22:09:58Z)
• SFTok: Bridging the Performance Gap in Discrete Tokenizers [72.9996757048065]
  We propose textbfSFTok, a discrete tokenizer that incorporates a multi-step iterative mechanism for precise reconstruction.<n>At a high compression rate of only 64 tokens per image, SFTok achieves state-of-the-art reconstruction quality on ImageNet.
  arXiv  Detail & Related papers  (2025-12-18T18:59:04Z)
• Image Tokenizer Needs Post-Training [76.91832192778732]
  We propose a novel tokenizer training scheme, focusing on improving latent space construction and decoding respectively.<n>Specifically, we propose a plug-and-play tokenizer training scheme, which significantly enhances the robustness of tokenizer.<n>We further optimize the tokenizer decoder regarding a well-trained generative model to mitigate the distribution difference between generated and reconstructed tokens.
  arXiv  Detail & Related papers  (2025-09-15T21:38:03Z)
• Fast constrained sampling in pre-trained diffusion models [80.99262780028015]
  We propose an algorithm that enables fast, high-quality generation under arbitrary constraints.<n>Our approach produces results that rival or surpass the state-of-the-art training-free inference methods.
  arXiv  Detail & Related papers  (2024-10-24T14:52:38Z)
• SpotDiffusion: A Fast Approach For Seamless Panorama Generation Over Time [7.532695984765271]
  We present a novel approach to generate high-resolution images with generative models.<n>Our method shifts non-overlapping denoising windows over time, ensuring that seams in one timestep are corrected in the next.<n>Our method offers several key benefits, including improved computational efficiency and faster inference times.
  arXiv  Detail & Related papers  (2024-07-22T09:44:35Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• Fast Image-Anomaly Mitigation for Autonomous Mobile Robots [27.049498074025088]
  Camera anomalies like rain or dust can severelydegrade image quality and its related tasks. In this work we address this importantissue by implementing a pre-processing step that can effectivelymitigate such artifacts in a real-time fashion.
  arXiv  Detail & Related papers  (2021-09-04T15:39:42Z)

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.