Pith. sign in

REVIEW 10 cited by

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.06313 v4 pith:3ZOGMKQM submitted 2023-10-10 cs.CV

Fei Shen , Hu Ye , Jun Zhang , Cong Wang , Xiao Han , Wei Yang This is my paper · ORCID
classification cs.CV
keywords imagediffusionconditionalstagetargetmodelpcdmspose
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent work has showcased the significant potential of diffusion models in pose-guided person image synthesis. However, owing to the inconsistency in pose between the source and target images, synthesizing an image with a distinct pose, relying exclusively on the source image and target pose information, remains a formidable challenge. This paper presents Progressive Conditional Diffusion Models (PCDMs) that incrementally bridge the gap between person images under the target and source poses through three stages. Specifically, in the first stage, we design a simple prior conditional diffusion model that predicts the global features of the target image by mining the global alignment relationship between pose coordinates and image appearance. Then, the second stage establishes a dense correspondence between the source and target images using the global features from the previous stage, and an inpainting conditional diffusion model is proposed to further align and enhance the contextual features, generating a coarse-grained person image. In the third stage, we propose a refining conditional diffusion model to utilize the coarsely generated image from the previous stage as a condition, achieving texture restoration and enhancing fine-detail consistency. The three-stage PCDMs work progressively to generate the final high-quality and high-fidelity synthesized image. Both qualitative and quantitative results demonstrate the consistency and photorealism of our proposed PCDMs under challenging scenarios.The code and model will be available at https://github.com/tencent-ailab/PCDMs.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MVL-Loc: Leveraging Vision-Language Model for Generalizable Multi-Scene Camera Relocalization

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MVL-Loc fuses CLIP image and text features with per-scene pose heads and reports state-of-the-art multi-scene relocalization accuracy on 7Scenes and Cambridge Landmarks.

  2. 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly

    cs.CV 2025-02 conditional novelty 6.0 of 10

    3CAD is a large real-world dataset for 3C product anomaly detection with multiple defect types per image, and the proposed CFRG method sets the state of the art on it.

  3. ACM-UNet: Adaptive Integration of CNNs and Mamba for Efficient Medical Image Segmentation

    cs.CV 2025-05 conditional novelty 5.0 of 10

    ACM-UNet, a UNet variant combining pretrained CNN and Mamba backbones via lightweight adapters and a wavelet decoder module, reports 85.12% Dice on Synapse and 92.29% on ACDC.

  4. PQ-DAF: Pose-driven Quality-controlled Data Augmentation for Data-scarce Driver Distraction Detection

    cs.CV 2025-08 reject novelty 4.0 of 10

    PQ-DAF uses pose-conditioned diffusion generation plus CogVLM filtering to augment few-shot driver distraction training data, and reports large accuracy gains that are compromised by a non-standard train/test protocol.

  5. Hybrid Compact Least-Squares and Central Weighted Essentially Non-Oscillatory Schemes for Hyperbolic Conservation Laws on Structured Curvilinear Grids

    physics.flu-dyn 2025-08 reject novelty 4.0 of 10

    No verifiable result: the abstract and body address unrelated topics, so the claimed CLS-CWENO schemes appear without derivation, experiments, or benchmarks.

  6. DiffFit: Disentangled Garment Warping and Texture Refinement for Virtual Try-On

    cs.CV 2025-06 reject novelty 4.0 of 10

    DiffFit synthesizes virtual try-on images by separately warping the garment geometry and then refining texture with a conditional diffusion model, reporting SOTA metrics on VITON-HD and DressCode but with inconsistent...

  7. O2Former:Direction-Aware and Multi-Scale Query Enhancement for SAR Ship Instance Segmentation

    cs.CV 2025-06 conditional novelty 4.0 of 10

    O2Former adds a multi-scale query generator and an orientation-aware module to Mask2Former and reports improved SAR ship instance segmentation on SSDD and HRSID.

  8. Dual Attention Residual U-Net for Accurate Brain Ultrasound Segmentation in IVH Detection

    eess.IV 2025-05 conditional novelty 4.0 of 10

    A residual U-Net with CBAM and a dual-branch sparse/dense attention layer reports Dice 89.04 and IoU 81.84 on brain ultrasound ventricle segmentation.

  9. MCFNet: A Multimodal Collaborative Fusion Network for Fine-Grained Semantic Classification

    cs.CV 2025-05 conditional novelty 3.0 of 10

    MCFNet fuses ALBERT text features and ViT image features with dropout, L1/L2 regularization, hybrid self/cross attention, and multi-loss training, claiming state-of-the-art accuracy on Con-Text and Drink Bottle.

  10. FreqU-FNet: Frequency-Aware U-Net for Imbalanced Medical Image Segmentation

    eess.IV 2025-05 reject novelty 3.0 of 10

    FreqU-FNet mixes frequency-domain filters and adaptive upsampling inside a U-Net, and claims better minority-class segmentation, although key reported results are internally inconsistent.

Pith tools