This work proposes a pixel-grounded super-resolution (PGSR) framework that preserves LR-observed pixel evidence before VAE compression and reuses it throughout restoration and improves the realism--fidelity trade-off and produces more faithful, visually convincing results than existing latent generative SR approaches.
Abstract
Image super-resolution (SR) with large generative models has recently achieved remarkable perceptual quality, yet maintaining fidelity to the LR observation remains challenging. In particular, we observe that diffusion transformers (DiTs) built on latent representations suffer from a critical limitation: the compression bottleneck of the VAE weakens fine-grained spatial information, leading to hallucinated details that are weakly grounded in the input image. In this work, we revisit generative SR from a representation perspective and propose a pixel-grounded super-resolution (PGSR) framework that preserves LR-observed pixel evidence before VAE compression and reuses it throughout restoration. Instead of relying solely on the compressed latent condition, PGSR extracts pre-VAE pixel evidence from the upsampled LR image and reuses it at two stages. First, Condition-Side Trajectory Guidance fuses LR-derived pixel evidence with the latent LR condition to guide the latent restoration trajectory. Second, Decoder-Side Pixel Grounding injects multi-scale pixel features into the frozen VAE decoder to ground the final rendering with LR-observed cues. To efficiently adapt large pretrained DiT models, we keep the latent autoencoder and main flow-matching backbone frozen, and train only lightweight restoration modules. We further study an efficient local-window attention variant for improved high-resolution efficiency and scalability. Extensive experiments demonstrate that PGSR improves the realism--fidelity trade-off and produces more faithful, visually convincing results than existing latent generative SR approaches.
PixRestore is presented, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining.
Lingchen Sun, Rongyuan Wu, Xiangtao Kong et al.· 0 citations
Latent diffusion models (LDMs) enable efficient high-resolution image synthesis by denoising in a VAE-compressed latent space. However, fixed visual tokenizers can discard fine textures and structural details, while separate representation and diffusion training creates a mismatch between reconstruction and generation objectives. These limitations have renewed interest in pixel-space diffusion, which models raw pixels directly, removes the VAE bottleneck, and supports end-to-end optimization. This formulation better matches the demands of high-fidelity generation but introduces challenges in high-dimensional modeling, including noise scheduling, loss weighting, token efficiency, and scalable architecture design. Pixel-space modeling also offers a promising basis for unified multimodal systems: raw pixels, text, and task conditions can be represented in a shared token space and jointly processed by a single Transformer, narrowing the gap between visual understanding and generation. This paper reviews Pixel-Space Diffusion Transformers (pDiTs) from the perspectives of model architecture, continuous generative mechanisms, and unified multimodal modeling. We summarize representative methods, identify key technical challenges, and discuss future directions toward high-fidelity, end-to-end vision foundation models that integrate generation and understanding.
Renye Yan, Jikang Cheng, You Wu et al.· 2 citations
Real-world image super-resolution (Real-ISR) aims to reconstruct high-quality (HQ) images from low-quality (LQ) inputs subject to diverse real-world degradations. Recent advances have leveraged the LQ inputs and natural image priors learned by Stable Diffusion models to achieve impressive results. However, existing methods often overlook insufficient clarity of LQ inputs inevitably induce content drift in the generated HQ images. This manifests primarily as visual detail degradation and textual semantic shift, severely compromising both fidelity and perceptual quality. To address this challenge, we propose FSP-Diff, a novel one-step diffusion model featuring a dual-pathway architecture. This architecture comprises a Detail-Conditioned Pathway for injecting structured details to recover fine structures, and a Detail-Modulated Semantic Pathway that refines semantic guidance using structured details to mitigate semantic deviations. Extensive experiments on standard Real-ISR benchmarks demonstrate that FSP-Diff surpasses existing one-step diffusion methods in both quantitative and qualitative metrics.
Chunxiao Liu, Wei Liu, Anbin Xiong et al.· 0 citations
High-Compression videos suffer from severe distortions, among which degradation in person regions has the greatest impact on viewers’ immersive experience. Existing quality enhancement techniques usually focus on overall image denoising or super-resolution, often overlooking the crucial recovery of fine structures in these essential person regions. To address these challenges, the research introduces a novel framework titled Person Region Restoration Driven by Perceptual Fidelity (PRRDPF), which combines long-range dependency features with perceptual structure loss for enhanced generative restoration. Specifically, first, the research constructs a high-fidelity distorted person-region dataset via a closed-loop degradation pipeline, addressing the lack of paired datasets. Secondly, a Temporal Gated Fusion (TGF) block is designed to use gated convolutions for selectively recovering high-frequency features while capturing local and global dependencies. Finally, a Structural Similarity Index Measure (SSIM)-based dynamic weighted adversarial loss is proposed to prioritize the restoration of visual texture details. Experimental results validate that PRRDPF significantly outperforms the best models in Peak Signal-to-Noise Ratio (PSNR), SSIM, and Learned Perceptual Image Patch Similarity (LPIPS), effectively mitigating artifacts and enhancing clarity in person visuals. This framework presents a promising approach for intelligent video coding integrated with generative artificial intelligence and holds significant potential for practical applications.
Linyun Liu, Li Yu, Jiaxin Zeng et al.· IEEE Signal Processing Lette...· 0 citations
All-in-one image restoration seeks a single model that can recover images degraded by diverse and spatially non-uniform corruptions. However, many unified Transformers rely on fixed patch partitioning: task/degradation condition is injected only into the backbone blocks after tokenization, leaving the embedding and reconstruction stages insensitive to local degradation variations. In contrast to previous approaches, we present Flexible Image Transformer (FIT) that explicitly models degradation awareness across the entire pipeline, from patch sampling to pixel reconstruction. Specifically, FIT employs a lightweight Degradation Encoder to predict a global degradation vector $\mathbf{g}$ and a spatial degradation map $\mathbf{M}$ from local degradation severity, which jointly condition the patch embedding and unembedding through adaptive deformation. Moreover, to improve robustness across degradation types, we introduce a task-token dropout strategy that regularizes task conditioning during training. On five standard benchmarks (BSD68, Rain100L, SOTS, GoPro, and LOLv1), FIT achieves state-of-the-art performance with 30.72 dB average PSNR on the five-degradation setting and 32.83 dB on the three-degradation setting, outperforming recent unified restoration methods by +0.5$\sim$1.1 dB. Moreover, the learned offsets provide a direct handle for visualizing degradation-aware spatial adaptation.
Zihao He, Yunfeng Wu, Xinchao Wang et al.· 0 citations
PixSDS is proposed, a lightweight VAE-consistent gradient repair method that decodes a latent SDS lookahead step and uses the decoded image as a clean direction for pixel-space optimization, reducing motion in VAE-inconsistent directions without retraining the diffusion model, changing the renderer, or replacing the SDS objective.