arXiv Computer Vision
Efficient Image Synthesis with Sphere Latent Encoder
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 2
Sphere Encoder 2
Sphere Encoder 2 is an improved autoencoder that generates images by decoding random points from a high‑dimensional latent sphere. The original Sphere Encoder suffered from two key limitations: (1) random latent points cluster near the equator, a region never reached during training, creating a gap that hampers one‑step generation; (2) pixel‑wise reconstruction loss causes the decoder to average plausible images, resulting in blurry outputs lacking high‑frequency detail. Sphere Encoder 2 addresses both issues, yielding substantially better image quality while preserving the speed and simplicity of an autoencoder.
arXiv Computer Vision
4d ago
Scaling Transformer Energy-based Models For High Quality Image Synthesis
arXiv:2610.31889v1 Announce Type: cross Abstract: Energy-Based Models (EBMs) are a flexible class of generative models that decouple probabilistic modeling from the generation process. This decouplin...
arXiv AI
Sep 30
HiRAE: Hierarchical Representation Autoencoding with Residual Budgets
arXiv:2609.37775v1 Announce Type: cross Abstract: Pretrained visual representations support image generation, but may not fully preserve the fine-grained details needed for faithful reconstruction. M...
arXiv AI
Oct 19
Rethinking the design space of Vanilla Pixel Diffusion Transformers
The paper revisits pixel-space diffusion models, showing that a vanilla diffusion transformer can generate directly in pixel space by swapping velocity prediction for clean image prediction. It introduces MFlow, an adaptive parameterization that interpolates between these two prediction modes based on data representation and model capacity, and demonstrates competitive performance on ImageNet, UCF‑101, and text‑to‑image tasks. Additionally, the authors add ConvRefiner, a lightweight convolutional module trained post‑hoc to restore high‑frequency details while preserving FID.
Hugging Face Trending Papers
Aug 17
PixRestore: Unified Image Restoration via Pixel Diffusion Transformer
Unified image restoration (UIR) aims to recover high-quality (HQ) content from low-quality (LQ) images with different degradations using a single model. Most recent methods adapt large pretrained text-to-image (T2I) latent diffusion models for their strong capacity and generative priors.
arXiv Computer Vision
Oct 1
DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
arXiv:2609.39222v1 Announce Type: new Abstract: High-compression tokenizers are essential for scaling latent image generative models. However, aggressive compression creates a fundamental tradeoff be...