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.
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.
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
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.
The proposed DuSPiT uses a compact base branch for efficient global reasoning and a parallel, high-capacity pixel branch, organized into subpatch groups, to preserve detailed appearance, with the two branches interacting through cross-attention.
Yunpeng Bai, Yossi Gandelsman, Michael Gharbi· 0 citations
An efficient aligned kernel network (AKNet) is proposed, which innovatively employs super-large convolution kernels to capture global receptive fields with minimal computational overhead, effectively mimicking the long-range dependency modeling of transformers.
Wan Li, Xiao-Lin Zhang· The Visual Computer· 0 citations
Despite the success of diffusion models in Video Frame Interpolation (VFI), existing methods still suffer from two critical limitations. First, latent diffusion inevitably loses fine-grained details when reconstructing images from latent representations back to the pixel space. Second, multi-step sampling incurs prohibitive memory consumption and inference latency. To address these issues, we propose SPEED, a one-step pixel diffusion framework for high-quality VFI. Specifically, SPEED employs a progressive multi-stage architecture with dynamic patch scaling to effectively learn multi-scale motion, structural, and appearance representations. Furthermore, we propose a novel Noise-Update-Only Attention mechanism to prevent semantic degradation of the clean condition frames while reducing the computational overhead by nearly 50%. Besides, we introduce a Drift-aware Timestep Sampling strategy coupled with a tailored training objective to directly predict images in the pixel space, enabling one-step inference without compromising the quality of the generated frames. Extensive experiments show that SPEED achieves state-of-the-art performance. On SNU-FILM, SPEED reduces LPIPS by 8.8% while delivering 63.3% faster inference and 10.6% lower memory usage. On challenging 4K benchmarks, it further surpasses prior methods by up to 51.5% in LPIPS.
Zihao Zhang, Haoyu Zhao, Siqian Yang et al.· 0 citations