Cover Image

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dong, Hejun, Niu, Junbo, Wang, Bin, Zeng, Weijun, Zhang, Wentao, He, Conghui
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
by: Wang, Bin, et al.
Published: (2026)

MinerU: An Open-Source Solution for Precise Document Content Extraction
by: Wang, Bin, et al.
Published: (2024)

MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
by: Xu, Bangrui, et al.
Published: (2026)

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
by: Niu, Junbo, et al.
Published: (2025)

Uni-Renderer: Unifying Rendering and Inverse Rendering Via Dual Stream Diffusion
by: Chen, Zhifei, et al.
Published: (2024)

Native Visual Understanding: Resolving Resolution Dilemmas in Vision-Language Models
by: Niu, Junbo, et al.
Published: (2025)

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
by: Zhang, Junyuan, et al.
Published: (2024)

DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models
by: Liang, Ruofan, et al.
Published: (2025)

AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation
by: Wang, Zhengren, et al.
Published: (2026)

DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM
by: Zhang, Qintong, et al.
Published: (2025)

DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering
by: Zheng, Rongjia, et al.
Published: (2025)

MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors
by: Litman, Yehonathan, et al.
Published: (2024)

Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
by: Liang, Hao, et al.
Published: (2025)

CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
by: Ma, Dongsheng, et al.
Published: (2026)

Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering
by: Sun, Shanlin, et al.
Published: (2025)

Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes
by: Choi, JunYong, et al.
Published: (2025)

Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance
by: Enyo, Yuto, et al.
Published: (2023)

IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination
by: Chen, Xi, et al.
Published: (2024)

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering
by: Liang, Ruofan, et al.
Published: (2024)

PICD: Versatile Perceptual Image Compression with Diffusion Rendering
by: Xu, Tongda, et al.
Published: (2025)

EVQAScore: A Fine-grained Metric for Video Question Answering Data Quality Evaluation
by: Liang, Hao, et al.
Published: (2024)

DODO: Discrete OCR Diffusion Models
by: Man, Sean, et al.
Published: (2026)

SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
by: Peng, Yibo, et al.
Published: (2026)

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
by: Zou, Chang, et al.
Published: (2024)

Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework
by: Shi, Linxiao, et al.
Published: (2026)

Multimodal OCR: Parse Anything from Documents
by: Zheng, Handong, et al.
Published: (2026)

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
by: Zhao, Zhiyuan, et al.
Published: (2024)

SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering
by: Niu, Jiahao, et al.
Published: (2026)

Many-Worlds Inverse Rendering
by: Zhang, Ziyi, et al.
Published: (2024)

TextSR: Diffusion Super-Resolution with Multilingual OCR Guidance
by: Ye, Keren, et al.
Published: (2025)

Demystifying Numerosity in Diffusion Models -- Limitations and Remedies
by: Zhao, Yaqi, et al.
Published: (2025)

Denoising Monte Carlo Renders with Diffusion Models
by: Vavilala, Vaibhav, et al.
Published: (2024)

TensoIR: Tensorial Inverse Rendering
by: Jin, Haian, et al.
Published: (2023)

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
by: Zeng, Yu, et al.
Published: (2024)

Denoising Diffusion via Image-Based Rendering
by: Anciukevičius, Titas, et al.
Published: (2024)

HuGDiffusion: Generalizable Single-Image Human Rendering via 3D Gaussian Diffusion
by: Tang, Yingzhi, et al.
Published: (2025)

EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering
by: Lu, Runnan, et al.
Published: (2025)

GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
by: Shi, Yahao, et al.
Published: (2023)

FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
by: Liu, Zheng, et al.
Published: (2025)

OmniDocLayout: Towards Diverse Document Layout Generation via Coarse-to-Fine LLM Learning
by: Kang, Hengrui, et al.
Published: (2025)