ENet-GP: Unified Document Image Restoration

Sujal Burad; Aakanksha; A. N. Rajagopalan; Sumit Shekar

cs.CVSep 27, 2026

ENet-GP: Unified Document Image Restoration

Authors: Sujal Burad, Aakanksha, A. N. Rajagopalan, Sumit Shekar

Organizations: Indian Institute of Technology, Madras · Adobe, India

Abstract

Reliable document digitization in uncontrolled capture settings is challenging because real images exhibit multiple interacting degradations rather than a single isolated distortion. Documents thus captured are affected simultaneously by geometric distortions, like page warping, as well as photometric degradations such as non-uniform illumination, and blurring. However, most existing approaches address these factors independently and are evaluated on benchmarks containing only one distortion type, limiting their real-world applicability. We introduce GutenDoc, a large-scale dataset of high-resolution dense-text documents with physically grounded compound degradations. Using physics-based rendering, our dataset jointly models geometric warping and diverse photometric effects, enabling systematic evaluation under realistic capture conditions. We further propose a unified restoration framework that jointly corrects geometric and photometric distortions within a single-network and single-training setup, without the need for degradation-specific retraining or sequential inference passes. Extensive experiments show that our method remains competitive on established single-distortion benchmarks while substantially improving robustness under compound degradations, providing a practical solution for real-world document digitization.

Figures & tables

Figure 1 : Top figure: Degradation comparison between previous Document Restoration datasets and our proposed document dataset, GutenDoc. Bottom figure: Unlike previous cascaded methods that require sequential ordering and multiple passes with iterative evaluation to find the optimal ordering, our proposed unified network, ENet-GP restores any combination of document degradations in a single-pass using a single-network-single-training setup paradigm.

Task	Real-World Datasets (Size)	Synthetic Datasets (Size)
Dewarping	DocUnet (130) [ 46 ] , DIW(5k) [ 45 ] , DIR300 (300) [ 17 ] , Inv3DReal (360) [ 23 ] , DocReal(200) [ 81 ] , WarpDoc-R(840) [ 91 ] , UDIR (195) [ 13 ] , Book100 (100) [ 43 ] , WarpDoc (1k) [ 78 ] , UVDoc (50) [ 70 ]	Doc3D (100k) [ 7 ] , UVDoc (pseudo-realistic)(20k) [ 70 ] , Inv3d (25k) [ 23 ] , DICP (30k) [ 77 ] , [ 37 ] (90k), Book3D (56k) [ 43 ] , AlignSynth [ 88 ]
Deshadowing	RDD (4.9k) [ 89 ] , Kligler (300) [ 33 ] , Jung (87) [ 31 ] , OSR (237) [ 71 ] , WEZUT (176) [ 51 ]	FSDSRD (14.2k) [ 48 ] , SynDocDS (50k) [ 49 ] , SD7k [ 39 ]
Appearance	DocAligner (130) [ 88 ] , RealDAE (600) [ 85 ]	Doc3DShade (90k) [ 8 ] , DocProj (2.4k) [ 38 ]
Binarization	(H)-DIBCO [ 57 , 19 , 52 , 53 , 54 , 55 , 56 , 58 , 59 , 60 ] , Synchromedia(240) [ 21 ] , Persian Heritage(15) [ 2 ] , Bickley Diary (7) [ 12 ]	Noisy Office (216) [ 84 ]
Deblurring	TDD [ 28 ] (used for both training and benchmarking)

Table 1 : Summary of existing DIR datasets.

Category	Representative Methods	Core Mechanisms	Primary Limitations
Geometric Networks	DocUNet [ 46 ] , DewarpNet [ 7 ] , DocTr [ 14 ] , DvD [ 90 ]	U-Net, 3D coordinate prediction, Transformers, Diffusion models	Treat shape correction in isolation; fail to address accompanying photometric distortions.
Photometric Networks	Skip-connections [ 20 , 47 , 93 ] , General [ 1 , 6 , 82 ] , SwinIR [ 40 ] , Restormer [ 83 ] , Uformer [ 75 ] , DocEnTr [ 67 ] , DocDeshadower [ 94 ] , BGSNet [ 89 ] , DocDiff [ 79 ]	Residual learning, Vision Transformers (Self-attention, Frequency-aware), Diffusion models	Assume a spatially aligned, flat surface; struggle with geometry-induced lighting variations.
Unified Solvers	ProRes [ 44 ] , DocRes [ 87 ] , UniDocDiff [ 92 ] , Tang et al. [ 68 ] , DocNLC [ 72 ]	Learnable/Dynamic prompting, Diffusion, Dual-stream networks, Contrastive learning	Struggle to synergistically model the intrinsic correlation between 3D deformations and photometric distortions.

Table 2 : Overview of DIR architectures.

Figure 3 : GutenDoc dataset example with corresponding distortion type.(See Table 4 ).

Figure 5 : The proposed architecture, ENet-GP. The Joint Feature Encoder (the middle arm) captures features for both photometric and geometric distortions. Geometric Rectification decoder (the top arm) produces backward mapping and document mask region of the input image to solve for only geometric degradations. Photometric Rectification Decoder (the bottom arm) produces only photometric degradation free image inside the document mask region. These two outputs are combined to produce the final geometric and photometric distortion free image.

Combination	Model	Trained on	Group	Tested on	Inference Passes				Image Metrics		Text Metrics		Average Wall-clock Time (s) $\downarrow$	GFLOPs $\downarrow$
Combination	Model	Trained on	Group	Tested on	1st	2nd	3rd	4th	PSNR $\uparrow$ /	SSIM $\uparrow$ /	CER $\downarrow$	ED $\downarrow$	Average Wall-clock Time (s) $\downarrow$	GFLOPs $\downarrow$
1	ENet-GP	GutenDoc (Train and Val split) (see Table 4 )	$A\rightarrow$	GutenDoc Test split (Table 4 )	Perspective All	–	–	–	22.1313	0.6551	0.5118	1493.8311	0.439	280.2937
	DocRes		$A^{\prime}\rightarrow$ $\left.\vbox{\vrule height=0.0pt,width=0.0pt}\textnormal{\hbox{}}\right\{$	GutenDoc Test split (Table 4 )	Dew	–	–	–	16.4945	0.6309	0.8622	2581.0497	1.5326	183.6135
					Dew	Des	–	–	22.5562	0.7309	0.9767	2928.8002	1.9852	367.227
					Dew	App	–	–	22.5499	0.7307	0.9738	2917.6717	1.6372	367.227
					Dew	Deb	–	–	22.6066	0.7307	0.9768	2928.8490	1.9092	367.227

Table 5 : Comparison of ENet-GP and DocRes [ 87 ] on GutenDoc testing dataset. For each metric, the best result achieved across a group and its associated prime rows (row

A

and rows of

A^{\prime}

, row

B

and rows of

B^{\prime}

) is highlighted in bold .“

\downarrow

” means lower is better. “

\uparrow

” means higher is better.

Combination	Model	Trained on	Group	Tested on	Inference Passes	Image Metrics		Text Metrics		Average Wall-clock Time (s) $\downarrow$	GFLOPs $\downarrow$
Combination	Model	Trained on	Group	Tested on	1st	PSNR $\uparrow$ / (LD) $\downarrow$	SSIM $\uparrow$ / (MSSIM) $\uparrow$	CER $\downarrow$	ED $\downarrow$	Average Wall-clock Time (s) $\downarrow$	GFLOPs $\downarrow$
2	ENet-GP	GutenDoc (Train and Val split) (see Table 4 )	$J\rightarrow$	DIR300 [ 16 ]	Perspective All	(15.9966)	(0.4980)	0.4951	1250.4833	1.4466	280.2937
			$K\rightarrow$	Kligler [ 33 ]	Perspective All	6.6137	0.3719	0.5431	115.7933	0.4660	280.2937
			$L\rightarrow$	Jung [ 31 ]	Perspective All	15.2150	0.7626	0.9537	545.5747	0.4660	280.2937
			$M\rightarrow$	OSR [ 71 ]	Perspective All	12.5555	0.8549	0.2662	299.9451	0.4660	280.2937
			$N\rightarrow$	TDD [ 28 ]	Perspective All	7.9188	0.2823	0.8843	136.3169	0.4167	280.2937

Table 6 : Comparison of ENet-GP and DocRes [ 87 ] on individual task-specific testing dataset of IDD. For each metric, the best result achieved across a group and its associated prime row (e.g.

C

and

C^{\prime}

row,

D

and

D^{\prime}

row,…) is highlighted in bold .“

\downarrow

” means lower is better. “

\uparrow

” means higher is better.

Table 10

Figure 6 : Left: Visual comparison of input image from GutenDoc testing split (Table 4 ); restored output from corresponding inference sequence of DocRes [ 87 ] selected from Table 5 ; restored output from ENet-GP; and ground truth. Image is washed out for Type J1, J2, D, and E for the corresponding sequential pass of DocRes. ENet-GP output is closely aligned with Ground Truth. Red boxes highlight the regions of stretches, squeeze, and curves in the output. Yellow boxes highlights the background region present in the output. Right: Sequential transformation of image as in 4-inference pass sequences of DocRes( $Dew_{1}$ , $Deb_{2}$ , $Des_{3}$ , $App_{4}$ ) (from Table 5 ) which starts with dewarping, then followed by deblurring, deshadowing, and finally appearance enhancement. It depicts the error accumulation as mentioned in [ 87 ] paper.

Explore similar work

DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation
Aug 10, 2026Lingming Su, Wanglong Lu, Tao Wang +4Degradation Wavelets
College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China · College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China · AI Analytics Team, Nasdaq, St. John's, Canada +2
SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction
Sep 14, 2026Daniel Woortmann, Tanguy Magne, Olga Sorkine-HornungSynthetic-To-Real Domain Gap Large-Scale 3D Editing Dataset
ETH Zurich, Department of Computer Science, Universitätstrasse 6, 8092 Zurich, Switzerland
Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration
Aug 7, 2026Zihao He, Yunfeng Wu, Xinchao Wang +1Image Restoration Degradation
School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China · Alibaba Group, Beijing, China · School of Advanced Technology, Xi’an Jiaotong-Liverpool University, Suzhou, China +1

Aug 10, 2026, cs.CVJ/K move · Enter open · S save

DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation

Lingming Su, Wanglong Lu, Tao Wang, Kaihao Zhang+3

College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China · College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China · AI Analytics Team, Nasdaq, St. John's, Canada+2

Degradation Wavelets High-Frequency Reconstruction Prior Knowledge Integration

Open paper AskPDF arXiv

High-quality document images are pivotal for information archiving and downstream automatic processing. However, they are frequently compromised by diverse degradations during uncontrolled acquisition and transmission. While unified document restoration techniques have been proposed to restore images from multiple degradations, they often struggle with training multiple degradation-specific models, reliance on manual task-specific prompts, or cross-task data pairing. To address these limitations, we propose DocPure, a prompt-free unified framework that achieves degradation-aware document restoration. We design a degradation-aware structure auto-encoder with degradation-informed routing regularization to predict clean structural priors from degraded inputs. The model is prompt-free at inference, and degradation labels are only used as auxiliary supervision for the routing regularization during training. Furthermore, we introduce a structure-guided wavelet interaction mechanism to bridge frequency-domain features and spatial semantics. Within the structure-guided wavelet interaction mechanism, a cross-frequency adaptive modulation utilizes low-frequency sub-bands to modulate high-frequency recovery, ensuring structural consistency. Extensive experiments demonstrate that DocPure achieves strong performance compared with state-of-the-art methods across various tasks, including deblurring, denoising, compression artifact reduction, and deshadowing.

Abstract

Explore similar work

DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation

SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination Correction

Bend the Basics: Degradation-Aware Deformable Tokenization for All-in-One Image Restoration