PixRestore: Unified Image Restoration via Pixel Diffusion Transformer
Summary
PixRestore is a VAE-free pixel-space diffusion transformer for unified image restoration, achieving high fidelity and efficiency via flow matching and adversarial fine-tuning to a one-step generator.
View Cached Full Text
Cached at: 08/19/26, 11:57 AM
Paper page - PixRestore: Unified Image Restoration via Pixel Diffusion Transformer
Source: https://huggingface.co/papers/2608.16793
Abstract
PixRestore is a compact, VAE-free pixel-space diffusion transformer trained from scratch for unified image restoration, using flow matching on patchified pixels, DINO-based reliability-guided feature fusion, and adversarial fine-tuning to a one-step generator for efficient high-fidelity inference.
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. However, thevariational autoencoder(VAE) in latent T2I models may discard restoration-sensitive details, while the open-ended synthesis prior can introduce content-inconsistent artifacts. We present PixRestore, a VAE-free pixel-spaceDiffusion Transformer(DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining. PixRestore performsflow matchingdirectly onpatchified pixels, preserving fine-grained details while keeping the token sequence tractable. To adapt to different degradations, PixRestore learns to predict the reliability of layer features using LQ--HQDINO feature similarity. Features from more reliable layers are fused asdense conditioning, while less reliable layers receive stronger HQ-feature supervision to encourage degradation removal. We train PixRestore on a large-scale corpus of diverse scenes and degradations, and further finetune it into aone-step generatorusing DINO-basedadversarial objectivesfor efficient inference. Experiments on public benchmarks and real-world test sets show that, with only about 50M parameters and single-step inference, PixRestore achieves the best overall fidelity, perceptual quality, and robustness to degradations among competing UIR models while being far more efficient. Larger PixRestore variants can further boost performance, demonstrating the scalability of our pixel-space design. Code and the curated benchmark can be found at https://github.com/csslc/PixRestore.
View arXiv pageView PDFGitHub26Add to collection
Get this paper in your agent:
hf papers read 2608\.16793
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.16793 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.16793 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.16793 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
PixWorld presents a unified pixel-space diffusion approach for 3D scene reconstruction and generation, overcoming limitations of latent-space methods by using direct image-level supervision and geometry-aware feature alignment. The method outperforms prior generation methods and matches state-of-the-art reconstruction methods.
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
PointDiT presents a minimalist pixel-space diffusion transformer using a plain ViT architecture for monocular geometry estimation, outperforming complex latent-based models while maintaining simplicity and robustness in ambiguous regions.
@xuanchi13: The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models s…
NVIDIA introduces PiD, a Pixel Diffusion Decoder that replaces traditional VAE/RAE decoders in latent diffusion models, enabling fast, high-resolution decoding with up to 6× speedup and improved visual fidelity.
nvidia/PiD
NVIDIA releases PiD (Pixel Diffusion Decoder), a conditional pixel-space diffusion model that unifies latent-to-pixel decoding and upsampling into one generative module, producing super-resolved images in one pass. Model checkpoints and VAE weights are released under a non-commercial license.
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
PiD introduces a pixel diffusion decoder that reformulates latent decoding as conditional pixel diffusion, enabling fast and high-quality image synthesis at high resolutions with reduced computational requirements. It decodes latents into 4x or 8x upscaled images in under a second on consumer hardware.