TeleOCR-bf16 API & Inference Endpoint

🔥 News

2026/09/10 - We have renamed NaviDC-OCR to TeleOCR, and all subsequent model iterations will be developed and released under the TeleOCR version.
2026/09/01 - We noticed that EMNLP 2026 is hosting the Dr.DocBench Challenge, a document parsing competition. We evaluated NaviDC-OCR with its native weights, achieving better results than MinerU 2.5 Pro and PaddleOCR-VL 1.6. Detailed results are shown below dr.docbench-challenge. We welcome the use of NaviDC‑OCR for competitions. Going forward, we will continue to deliver competitive parsing models for the community.
2026/08/29 — Thanks to Nandraj for the GGUF conversion and llama.cpp support 🔗 NaviDC-OCR-GGUF, and to the community for sharing their experience deploying NaviDC-OCR on Ascend 910B!
2026/08/17 — NaviDC-OCR model weights and technical report have been released.

📖 Introduction

TeleOCR is a lightweight (~1.2B parameters), open-source Vision-Language Model designed specifically for document parsing.

Unlike existing methods that mainly target either digital documents or camera-captured documents, TeleOCR unifies both scenarios within a single framework.

Compared with previous document parsing models, TeleOCR introduces

Multi-node Consensus Voting (MCV) for automatic pseudo-label generation
Geometry-aware document modeling for camera-captured documents
Curvature-Guided Douglas-Peucker Sampling (CGDP)
Image-to-image self-verification for automatic data refinement
Progressive four-stage training pipeline
Content-Structure Decoupled Learning for tables and formulas

These techniques enable TeleOCR to achieve state-of-the-art performance on both digital and camera-captured document benchmarks while remaining lightweight enough for practical deployment.

📊 Experimental Results

TeleOCR achieves state-of-the-art performance on multiple public document parsing benchmarks.

Layout Visualization of Distorted Documents

To evaluate the model's ability to understand complex document deformations, we conduct a visual evaluation on the public dewarping datasets DocUNet and DIR300, with representative results shown in Figure. TeleOCR directly performs layout and content parsing on distorted documents without dewarping preprocessing or a dedicated rectification model, demonstrating robust parsing under complex geometric deformations.

Dr.DocBench Challenge

Table with columns: 模型, overall ↑, Text edit ↓, formula cdm ↑, Table teds ↑, order edit ↓
模型	overall ↑	Text edit ↓	formula cdm ↑	Table teds ↑	order edit ↓
Specialized VLMs
TeleOCR	67.96	0.1903	0.02	64.97	0.398
Mineru 2.5 pro	62.26

OmniDocBench v1.6

Table with columns: Model Type, Methods, Param, Overall ↑, Text Edit ↓, Formula CDM ↑, Table TEDS ↑, Table TEDS-S ↑, Read Order Edit ↓
Model Type	Methods	Param	Overall ↑	Text Edit ↓	Formula CDM ↑	Table TEDS ↑	Table TEDS-S ↑	Read Order Edit ↓
Specialized VLMs	TeleOCR	1.2B	96.87	0.027	96.36	97.05	98.52	0.122

Wild_OmniDocBench

Table with columns: Model Type, Methods, Param, Overall ↑, Text Edit ↓, Formula CDM ↑, Table TEDS ↑, Table TEDS-S ↑, Read Order Edit ↓
Model Type	Methods	Param	Overall ↑	Text Edit ↓	Formula CDM ↑	Table TEDS ↑	Table TEDS-S ↑	Read Order Edit ↓
Decoupled VLMs	TeleOCR	1.2B	88.53	0.1173	88.26	89.05	92.14	0.2011

PureDocBench

Table with columns: Model Type, Model, Clean Overall ↑, Clean Text ↓, Clean Formula ↑, Clean Table ↑, Digital Degraded Overall ↑, Digital Degraded Text ↓, Digital Degraded Formula ↑, Digital Degraded Table ↑, Real Degraded Overall ↑, Real Degraded Text ↓, Real Degraded Formula ↑, Real Degraded Table ↑
Model Type	Model	Clean Overall ↑	Clean Text ↓	Clean Formula ↑	Clean Table ↑	Digital Degraded Overall ↑	Digital Degraded Text ↓	Digital Degraded Formula ↑	Digital Degraded Table ↑	Real Degraded Overall ↑	Real Degraded Text ↓	Real Degraded Formula ↑	Real Degraded Table ↑
Decoupled VLM	TeleOCR

ICDAR2026 Sci-ImageMiner

Table with columns: #, Team, RMS, TEDS, Weighted
#	Team	RMS	TEDS	Weighted
1	TeleOCR	17.23	66.39	41.81
2	VLMinators	17.29	64.31	40.80
3	Ricoh_SRCB	16.23	61.12	38.67

🚀 Installation

bash

pip install transformers torch pillow

Quick Start

python

import htmlimport itertoolsimport jsonimport refrom dataclasses import dataclass from PIL import Imageimport torchfrom transformers import AutoProcessor, AutoModel @dataclassclass ContentBlock:    type: str    bbox: list[float]    angle: int | None = None    content: str | None = None  @dataclassclass TableCell:    text: str    start_row_offset_idx: int    end_row_offset_idx: int    start_col_offset_idx: int    end_col_offset_idx: int    row_span: int = 1    col_span: int = 1  OTSL_NL = "<nl>"OTSL_FCEL = "<fcel>"OTSL_ECEL = "<ecel>"OTSL_LCEL = "<lcel>"OTSL_UCEL = "<ucel>"OTSL_XCEL = "<xcel>"OTSL_TOKENS = [OTSL_NL, OTSL_FCEL, OTSL_ECEL, OTSL_LCEL, OTSL_UCEL, OTSL_XCEL]  def _otsl_extract_tokens_and_text(text: str):    pattern = "(" + "|".join(map(re.escape, OTSL_TOKENS)) + ")"    tokens = re.findall(pattern, text)    parts = [part for part in re.split(pattern, text) if part.strip()]    return tokens, parts  def _count_right(rows, row_idx, col_idx, tokens):    span = 0    while col_idx < len(rows[row_idx]) and rows[row_idx][col_idx] in tokens:        span += 1        col_idx += 1    return span  def _count_down(rows, row_idx, col_idx, tokens):    span = 0    while row_idx < len(rows) and col_idx < len(rows[row_idx]) and rows[row_idx][col_idx] in tokens:        span += 1        row_idx += 1    return span  def _otsl_parse_texts(parts, tokens):    rows = [list(row) for is_nl, row in itertools.groupby(tokens, lambda token: token == OTSL_NL) if not is_nl]    if not rows:        return [], []     max_cols = max(len(row) for row in rows)    for row in rows:        row.extend([OTSL_ECEL] * (max_cols - len(row)))     cells = []    row_idx = 0    col_idx = 0    for idx, part in enumerate(parts):        if part in (OTSL_FCEL, OTSL_ECEL):            cell_text = ""            right_offset = 1            if part != OTSL_ECEL and idx + 1 < len(parts) and parts[idx + 1] not in OTSL_TOKENS:                cell_text = parts[idx + 1].strip()                right_offset = 2             next_right = parts[idx + right_offset] if idx + right_offset < len(parts) else ""            next_bottom = rows[row_idx + 1][col_idx] if row_idx + 1 < len(rows) and col_idx < len(rows[row_idx + 1]) else ""            col_span = 1 + (_count_right(rows, row_idx, col_idx + 1, {OTSL_LCEL, OTSL_XCEL}) if next_right in {OTSL_LCEL, OTSL_XCEL} else 0)            row_span = 1 + (_count_down(rows, row_idx + 1, col_idx, {OTSL_UCEL, OTSL_XCEL}) if next_bottom in {OTSL_UCEL, OTSL_XCEL} else 0)            cells.append(TableCell(                text=cell_text,                row_span=row_span,                col_span=col_span,                start_row_offset_idx=row_idx,                end_row_offset_idx=row_idx + row_span,                start_col_offset_idx=col_idx,                end_col_offset_idx=col_idx + col_span,            ))        if part in (OTSL_FCEL, OTSL_ECEL, OTSL_LCEL, OTSL_UCEL, OTSL_XCEL):            col_idx += 1        elif part == OTSL_NL:            row_idx += 1            col_idx = 0    return cells, rows  def convert_otsl_to_html(otsl_content: str) -> str:    if otsl_content.startswith("<table") and otsl_content.endswith("</table>"):        return otsl_content     tokens, parts = _otsl_extract_tokens_and_text(otsl_content)    cells, rows = _otsl_parse_texts(parts, tokens)    if not cells or not rows:        return ""     grid = [[None for _ in range(len(rows[0]))] for _ in range(len(rows))]    for cell in cells:        for row_idx in range(cell.start_row_offset_idx, min(cell.end_row_offset_idx, len(rows))):            for col_idx in range(cell.start_col_offset_idx, min(cell.end_col_offset_idx, len(rows[0]))):                grid[row_idx][col_idx] = cell     html_rows = []    for row_idx, row in enumerate(grid):        html_rows.append("<tr>")        for col_idx, cell in enumerate(row):            if cell is None or cell.start_row_offset_idx != row_idx or cell.start_col_offset_idx != col_idx:                continue            attrs = ""            if cell.row_span > 1:                attrs += f' rowspan="{cell.row_span}"'            if cell.col_span > 1:                attrs += f' colspan="{cell.col_span}"'            html_rows.append(f"<td{attrs}>{html.escape(cell.text.strip())}</td>")        html_rows.append("</tr>")    return "<table>" + "".join(html_rows) + "</table>"  def post_process(blocks: list[ContentBlock]) -> list[ContentBlock]:    for block in blocks:        if block.type == "table" and block.content:            block.content = convert_otsl_to_html(block.content)        elif block.type == "equation" and block.content:            content = block.content.strip()            content = content.removeprefix("\\[").removesuffix("\\]").strip()            if not (content.startswith("$") and content.endswith("$")):                content = f"$${content}$$"            block.content = content    return [block for block in blocks if block.type != "equation_block"] def infer(image: Image.Image, prompt: str) -> str:    messages = [        {"role": "system", "content": "You are a helpful assistant."},        {"role": "user", "content": [            {"type": "image"},            {"type": "text", "text": prompt},        ]},    ]    chat_prompt = processor.apply_chat_template(        messages,        tokenize=False,        add_generation_prompt=True,    )    inputs = processor(        text=[chat_prompt],        images=[image.convert("RGB")],        padding=True,        return_tensors="pt",    ).to(device=model.device, dtype=model.dtype)    output_ids = model.generate(        **inputs,        use_cache=True,        max_new_tokens=4096,        do_sample=False,    )    output_ids = output_ids.cpu().tolist()[0][len(inputs.input_ids[0]):]    return processor.batch_decode(        [output_ids],        skip_special_tokens=True,        clean_up_tokenization_spaces=False,    )[0].strip()   processor = AutoProcessor.from_pretrained("StarDoc-AI/TeleOCR", trust_remote_code=True, use_fast=True)model = AutoModel.from_pretrained(    "StarDoc-AI/TeleOCR",    trust_remote_code=True,    torch_dtype=torch.bfloat16,).cuda().eval() # textimage=Image.open("./assets/text.png").convert("RGB")raw_text = infer(image, "Please output the text content from the image.")print(raw_text.strip()) # tableimage=Image.open("./assets/table.png").convert("RGB")raw_otsl = infer(image, "This is the image of a table. Please output the table in OTSL format.")print(convert_otsl_to_html(raw_otsl)) # formula image=Image.open("./assets/formula.png").convert("RGB")raw_formula = infer(image, "Please write out the expression of the formula in the image using LaTeX format.")formula_block = ContentBlock("equation", [0.0, 0.0, 1.0, 1.0], content=raw_formula)formula = post_process([formula_block])[0].contentprint(formula) #codeimage=Image.open("./assets/code.png").convert("RGB")raw_code = infer(image,"The image contains a code snippet, please output the parsing result.")print(raw_code.strip()) # layoutimage=Image.open("./assets/layout.jpg").convert("RGB")image = image.resize((1036, 1036), Image.Resampling.BICUBIC)raw_layout = infer(image, "Analyze the image layout.")print(raw_layout.strip()) # Distorted document layoutlayout_image = Image.open("./assets/layout_distorted.jpg").convert("RGB")layout_image = layout_image.resize((1036, 1036), Image.Resampling.BICUBIC)raw_layout = infer(layout_image, "\nMulti-point Layout Segmentation Analysis.")print(raw_layout.strip()) #scientific figureimage=Image.open("./assets/scientific_figure.png").convert("RGB")raw_scientific_figure = infer(image, "This is a scientific figure. Please extract the table implied by this figure.")print(convert_otsl_to_html(raw_scientific_figure))

If you would like to perform complete document parsing, please refer to our GitHub repository: https://github.com/caipeng328/NaviDC-OCR.

Citation

bibtex

@article{teleocr,  title={TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents},  author={Cai, Peng and Zou, Zhaofan and Liu, Shifa and Wang, Yikun and Tang, Jiawei and Yang, Kaicheng and Tong, Meng and He, Zhongjiang and Sun, Hao},  journal={arXiv preprint arXiv:2608.12898},  year={2026}}

Community Contributions

Thanks to Nandraj for the GGUF conversion and llama.cpp support! 🔗 NaviDC-OCR-GGUF

Acknowledgements

TeleOCR is built upon

MinerU
Qwen2.5-VL
Qwen3
Transformers
PyTorch
FlashAttention

We sincerely thank these excellent open-source projects.

Contact

If you have any questions, feel free to open an issue or contact us.

Local copy on this Mac

This folder is the BF16 source used to quantize TeleOCR on this Mac. groxaxo did not train it. The weights are the local copy of XingChen-AGI/TeleOCR revision e92585356c0d0b7b7a65938f3da035c6593cc9a6. The recorded SHA-256 of model.safetensors is 9817b18041bd96403f75e38a33b28ed0cd5fb2641f67eead673afabd3c408109. The upload keeps that file only when the hash still matches.

teleocr_mlx.py is the local MLX adapter for TeleOCR's 128-wide heads, bias-free projections, and per-head query/key RMSNorm. config.json sets model_file to that adapter. The official model card above is unchanged apart from this section.

Serve the parent directory and request model TeleOCR-bf16:

omlx serve --model-dir /path/to/parent --host 127.0.0.1 --port 8000

模型

overall ↑

Text edit ↓

formula cdm ↑

Table teds ↑

order edit ↓

Specialized VLMs

TeleOCR

67.96

0.1903

0.02

64.97

0.398

Mineru 2.5 pro

62.26

Model Type

Methods

Param

Overall ↑

Text Edit ↓

Formula CDM ↑

Table TEDS ↑

Table TEDS-S ↑

Read Order Edit ↓

Specialized VLMs

TeleOCR

1.2B

96.87

0.027

96.36

97.05

98.52

0.122

Model Type

Methods

Param

Overall ↑

Text Edit ↓

Formula CDM ↑

Table TEDS ↑

Table TEDS-S ↑

Read Order Edit ↓

Decoupled VLMs

TeleOCR

1.2B

88.53

0.1173

88.26

89.05

92.14

0.2011

Table with columns: Model Type, Model, Clean Overall ↑, Clean Text ↓, Clean Formula ↑, Clean Table ↑, Digital Degraded Overall ↑, Digital Degraded Text ↓, Digital Degraded Formula ↑, Digital Degraded Table ↑, Real Degraded Overall ↑, Real Degraded Text ↓, Real Degraded Formula ↑, Real Degraded Table ↑
Model Type	Model	Clean Overall ↑	Clean Text ↓	Clean Formula ↑	Clean Table ↑	Digital Degraded Overall ↑	Digital Degraded Text ↓	Digital Degraded Formula ↑	Digital Degraded Table ↑	Real Degraded Overall ↑	Real Degraded Text ↓	Real Degraded Formula ↑	Real Degraded Table ↑
Decoupled VLM	TeleOCR

Model Type

Model

Clean Overall ↑

Clean Text ↓

Clean Formula ↑

Clean Table ↑

Digital Degraded Overall ↑

Digital Degraded Text ↓

Digital Degraded Formula ↑

Digital Degraded Table ↑

Real Degraded Overall ↑

Real Degraded Text ↓

Real Degraded Formula ↑

Real Degraded Table ↑

Decoupled VLM

TeleOCR

Team

RMS

TEDS

Weighted

TeleOCR

17.23

66.39

41.81

VLMinators

17.29

64.31

40.80

Ricoh_SRCB

16.23

61.12

38.67

import htmlimport itertoolsimport jsonimport refrom dataclasses import dataclass from PIL import Imageimport torchfrom transformers import AutoProcessor, AutoModel @dataclassclass ContentBlock: type: str bbox: list[float] angle: int | None = None content: str | None = None @dataclassclass TableCell: text: str start_row_offset_idx: int end_row_offset_idx: int start_col_offset_idx: int end_col_offset_idx: int row_span: int = 1 col_span: int = 1 OTSL_NL = "<nl>"OTSL_FCEL = "<fcel>"OTSL_ECEL = "<ecel>"OTSL_LCEL = "<lcel>"OTSL_UCEL = "<ucel>"OTSL_XCEL = "<xcel>"OTSL_TOKENS = [OTSL_NL, OTSL_FCEL, OTSL_ECEL, OTSL_LCEL, OTSL_UCEL, OTSL_XCEL] def _otsl_extract_tokens_and_text(text: str): pattern = "(" + "|".join(map(re.escape, OTSL_TOKENS)) + ")" tokens = re.findall(pattern, text) parts = [part for part in re.split(pattern, text) if part.strip()] return tokens, parts def _count_right(rows, row_idx, col_idx, tokens): span = 0 while col_idx < len(rows[row_idx]) and rows[row_idx][col_idx] in tokens: span += 1 col_idx += 1 return span def _count_down(rows, row_idx, col_idx, tokens): span = 0 while row_idx < len(rows) and col_idx < len(rows[row_idx]) and rows[row_idx][col_idx] in tokens: span += 1 row_idx += 1 return span def _otsl_parse_texts(parts, tokens): rows = [list(row) for is_nl, row in itertools.groupby(tokens, lambda token: token == OTSL_NL) if not is_nl] if not rows: return [], [] max_cols = max(len(row) for row in rows) for row in rows: row.extend([OTSL_ECEL] * (max_cols - len(row))) cells = [] row_idx = 0 col_idx = 0 for idx, part in enumerate(parts): if part in (OTSL_FCEL, OTSL_ECEL): cell_text = "" right_offset = 1 if part != OTSL_ECEL and idx + 1 < len(parts) and parts[idx + 1] not in OTSL_TOKENS: cell_text = parts[idx + 1].strip() right_offset = 2 next_right = parts[idx + right_offset] if idx + right_offset < len(parts) else "" next_bottom = rows[row_idx + 1][col_idx] if row_idx + 1 < len(rows) and col_idx < len(rows[row_idx + 1]) else "" col_span = 1 + (_count_right(rows, row_idx, col_idx + 1, {OTSL_LCEL, OTSL_XCEL}) if next_right in {OTSL_LCEL, OTSL_XCEL} else 0) row_span = 1 + (_count_down(rows, row_idx + 1, col_idx, {OTSL_UCEL, OTSL_XCEL}) if next_bottom in {OTSL_UCEL, OTSL_XCEL} else 0) cells.append(TableCell( text=cell_text, row_span=row_span, col_span=col_span, start_row_offset_idx=row_idx, end_row_offset_idx=row_idx + row_span, start_col_offset_idx=col_idx, end_col_offset_idx=col_idx + col_span, )) if part in (OTSL_FCEL, OTSL_ECEL, OTSL_LCEL, OTSL_UCEL, OTSL_XCEL): col_idx += 1 elif part == OTSL_NL: row_idx += 1 col_idx = 0 return cells, rows def convert_otsl_to_html(otsl_content: str) -> str: if otsl_content.startswith("<table") and otsl_content.endswith("</table>"): return otsl_content tokens, parts = _otsl_extract_tokens_and_text(otsl_content) cells, rows = _otsl_parse_texts(parts, tokens) if not cells or not rows: return "" grid = [[None for _ in range(len(rows[0]))] for _ in range(len(rows))] for cell in cells: for row_idx in range(cell.start_row_offset_idx, min(cell.end_row_offset_idx, len(rows))): for col_idx in range(cell.start_col_offset_idx, min(cell.end_col_offset_idx, len(rows[0]))): grid[row_idx][col_idx] = cell html_rows = [] for row_idx, row in enumerate(grid): html_rows.append("<tr>") for col_idx, cell in enumerate(row): if cell is None or cell.start_row_offset_idx != row_idx or cell.start_col_offset_idx != col_idx: continue attrs = "" if cell.row_span > 1: attrs += f' rowspan="{cell.row_span}"' if cell.col_span > 1: attrs += f' colspan="{cell.col_span}"' html_rows.append(f"<td{attrs}>{html.escape(cell.text.strip())}</td>") html_rows.append("</tr>") return "<table>" + "".join(html_rows) + "</table>" def post_process(blocks: list[ContentBlock]) -> list[ContentBlock]: for block in blocks: if block.type == "table" and block.content: block.content = convert_otsl_to_html(block.content) elif block.type == "equation" and block.content: content = block.content.strip() content = content.removeprefix("\\[").removesuffix("\\]").strip() if not (content.startswith("$") and content.endswith("$")): content = f"$${content}$$" block.content = content return [block for block in blocks if block.type != "equation_block"] def infer(image: Image.Image, prompt: str) -> str: messages = [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": [ {"type": "image"}, {"type": "text", "text": prompt}, ]}, ] chat_prompt = processor.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, ) inputs = processor( text=[chat_prompt], images=[image.convert("RGB")], padding=True, return_tensors="pt", ).to(device=model.device, dtype=model.dtype) output_ids = model.generate( **inputs, use_cache=True, max_new_tokens=4096, do_sample=False, ) output_ids = output_ids.cpu().tolist()[0][len(inputs.input_ids[0]):] return processor.batch_decode( [output_ids], skip_special_tokens=True, clean_up_tokenization_spaces=False, )[0].strip() processor = AutoProcessor.from_pretrained("StarDoc-AI/TeleOCR", trust_remote_code=True, use_fast=True)model = AutoModel.from_pretrained( "StarDoc-AI/TeleOCR", trust_remote_code=True, torch_dtype=torch.bfloat16,).cuda().eval() # textimage=Image.open("./assets/text.png").convert("RGB")raw_text = infer(image, "Please output the text content from the image.")print(raw_text.strip()) # tableimage=Image.open("./assets/table.png").convert("RGB")raw_otsl = infer(image, "This is the image of a table. Please output the table in OTSL format.")print(convert_otsl_to_html(raw_otsl)) # formula image=Image.open("./assets/formula.png").convert("RGB")raw_formula = infer(image, "Please write out the expression of the formula in the image using LaTeX format.")formula_block = ContentBlock("equation", [0.0, 0.0, 1.0, 1.0], content=raw_formula)formula = post_process([formula_block])[0].contentprint(formula) #codeimage=Image.open("./assets/code.png").convert("RGB")raw_code = infer(image,"The image contains a code snippet, please output the parsing result.")print(raw_code.strip()) # layoutimage=Image.open("./assets/layout.jpg").convert("RGB")image = image.resize((1036, 1036), Image.Resampling.BICUBIC)raw_layout = infer(image, "Analyze the image layout.")print(raw_layout.strip()) # Distorted document layoutlayout_image = Image.open("./assets/layout_distorted.jpg").convert("RGB")layout_image = layout_image.resize((1036, 1036), Image.Resampling.BICUBIC)raw_layout = infer(layout_image, "\nMulti-point Layout Segmentation Analysis.")print(raw_layout.strip()) #scientific figureimage=Image.open("./assets/scientific_figure.png").convert("RGB")raw_scientific_figure = infer(image, "This is a scientific figure. Please extract the table implied by this figure.")print(convert_otsl_to_html(raw_scientific_figure))

@article{teleocr, title={TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents}, author={Cai, Peng and Zou, Zhaofan and Liu, Shifa and Wang, Yikun and Tang, Jiawei and Yang, Kaicheng and Tong, Meng and He, Zhongjiang and Sun, Hao}, journal={arXiv preprint arXiv:2608.12898}, year={2026}}

TeleOCR-bf16

README

🔥 News

📖 Introduction

📊 Experimental Results

Layout Visualization of Distorted Documents

Dr.DocBench Challenge

OmniDocBench v1.6

Wild_OmniDocBench

PureDocBench

ICDAR2026 Sci-ImageMiner

🚀 Installation

Quick Start

Citation

Community Contributions

Acknowledgements

Contact

Local copy on this Mac

Explore FriendliAI today

README

🔥 News

📖 Introduction

📊 Experimental Results

Layout Visualization of Distorted Documents

Dr.DocBench Challenge

OmniDocBench v1.6

Wild_OmniDocBench

PureDocBench

ICDAR2026 Sci-ImageMiner

🚀 Installation

Quick Start

Citation

Community Contributions

Acknowledgements

Contact

Local copy on this Mac