Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation

• URL: http://arxiv.org/abs/2606.20112v1
• Date: Thu, 18 Jun 2026 11:35:11 GMT
• Title: Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation
• Abstract summary: Pixel-Level Residual Diffusion Transformer (PRDiT) is an inherent generative framework that synthesizes high-quality 3D medical volumes directly at voxel-level.<n>PRDiT consistently outperforms state-of-the-art models, such as HA-GAN, 3D LDM and WDM-3D, achieving significantly lower 3D FID, MMD and Wasserstein distance scores.
• Score: 20.986333949052007
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating high-resolution 3D CT volumes with fine details remains challenging due to substantial computational demands and optimization difficulties inherent to existing generative models. In this paper, we propose the Pixel-Level Residual Diffusion Transformer (PRDiT), a scalable generative framework that synthesizes high-quality 3D medical volumes directly at voxel-level. PRDiT introduces a two-stage training architecture comprising 1) a local denoiser in the form of an MLP-based blind estimator operating on overlapping 3D patches to separate low-frequency structures efficiently, and 2) a global residual diffusion transformer employing memory-efficient attention to model and refine high-frequency residuals across entire volumes. This coarse-to-fine modeling strategy simplifies optimization, enhances training stability, and effectively preserves subtle structures without the limitations of an autoencoder bottleneck. Extensive experiments conducted on the LIDC-IDRI and RAD-ChestCT datasets demonstrate that PRDiT consistently outperforms state-of-the-art models, such as HA-GAN, 3D LDM and WDM-3D, achieving significantly lower 3D FID, MMD and Wasserstein distance scores.

Related papers

• FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation [48.928051741750124]
  We propose a scalable image-to-3DGS framework that boosts representation learning and cross-modal alignment during generation.<n>FLUX3D yields substantial improvements in appearance fidelity and significantly outperforms all state-of-the-art (SOTA) methods in generating high-quality 3DGS assets.
  arXiv  Detail & Related papers  (2026-06-23T17:52:21Z)
• Three-Step Conditional Diffusion 3D Reconstruction for Light-Field Microscopy [14.462955551711671]
  Light-field microscopy enables single-shot capture of multi-angular information from biological samples.<n>Traditional physics-based algorithms often suffer from limited spatial resolution, severe artifacts, and high computational costs.<n>This paper proposes a high-fidelity Three-Step Conditional Diffusion (TCD) 3D reconstruction method for LFM.
  arXiv  Detail & Related papers  (2026-05-24T09:16:35Z)
• Optimizing 3D Diffusion Models for Medical Imaging via Multi-Scale Reward Learning [7.493047521402676]
  This paper presents a method to enhance 3D diffusion models using Reinforcement Learning (RL) with multi-scale feedback.<n>We fine-tune the model using Proximal Policy Optimization (PPO), guided by a novel reward system that integrates both 2D slice-wise assessments and 3D analysis.<n>Our results indicate that incorporating RL feedback effectively steers the generation process toward higher quality distributions.
  arXiv  Detail & Related papers  (2026-03-06T11:30:55Z)
• ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting [63.138778159026934]
  We propose an adaptive optimization framework guided by excess risk decomposition, termed ERGO.<n> ERGO dynamically estimates the view-specific excess risk and adaptively adjust loss weights during optimization.<n>Experiments on the Google Scanned Objects dataset and the OmniObject3D dataset demonstrate the superiority of ERGO over existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-10T20:44:43Z)
• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention [54.15345846343084]
  We propose Ultra3D, an efficient 3D generation framework that significantly accelerates sparse voxel modeling without compromising quality.<n>Part Attention is a geometry-aware localized attention mechanism that restricts attention computation within semantically consistent part regions.<n>Experiments demonstrate that Ultra3D supports high-resolution 3D generation at 1024 resolution and achieves state-of-the-art performance in both visual fidelity and user preference.
  arXiv  Detail & Related papers  (2025-07-23T17:57:16Z)
• Introducing 3D Representation for Medical Image Volume-to-Volume Translation via Score Fusion [3.3559609260669303]
  We present Score-Fusion, a novel volumetric translation model that effectively learns 3D representations by ensembling perpendicularly trained 2D diffusion models in score function space.<n>We show that Score-Fusion achieves superior accuracy and volumetric fidelity in 3D medical image super-resolution and modality translation.
  arXiv  Detail & Related papers  (2025-01-13T15:54:21Z)
• SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation [74.07836010698801]
  We propose an SMPL-based Transformer framework (SMPLer) to address this issue. SMPLer incorporates two key ingredients: a decoupled attention operation and an SMPL-based target representation. Extensive experiments demonstrate the effectiveness of SMPLer against existing 3D human shape and pose estimation methods.
  arXiv  Detail & Related papers  (2024-04-23T17:59:59Z)
• StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D [88.66678730537777]
  We present StableDreamer, a methodology incorporating three advances. First, we formalize the equivalence of the SDS generative prior and a simple supervised L2 reconstruction loss. Second, our analysis shows that while image-space diffusion contributes to geometric precision, latent-space diffusion is crucial for vivid color rendition.
  arXiv  Detail & Related papers  (2023-12-02T02:27:58Z)
• Two-and-a-half Order Score-based Model for Solving 3D Ill-posed Inverse Problems [7.074380879971194]
  We propose a novel two-and-a-half order score-based model (TOSM) for 3D volumetric reconstruction. During the training phase, our TOSM learns data distributions in 2D space, which reduces the complexity of training. In the reconstruction phase, the TOSM updates the data distribution in 3D space, utilizing complementary scores along three directions.
  arXiv  Detail & Related papers  (2023-08-16T17:07:40Z)
• NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions [97.27105725738016]
  integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs) has transformed 3D-aware generation from single-view images. We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations.
  arXiv  Detail & Related papers  (2023-03-22T18:59:48Z)

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.