Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DeepSeek OCR

github.com

Post reply on HN
Print view View original

91–100 of 252 posts

Re: DeepSeek OCR

#91

Post by burpsnard »

pietz wrote: post #42

My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…

I've only used tesseract, 'recreationally', but i tried generating images of random chars to see what resolution/contrast/noise was minimally recognisable; shocked at how bad it was. heavily relies on language models of character sequences, pretty useless On 'line noise'

Re: DeepSeek OCR

#92

Post by singularfutur »

ellisd wrote: post #36

The paper makes no mention of Anna’s Archive. I wouldn’t be surprised if DeepSeek took advantage of Anna’s offer granting OCR researchers access to their 7.5 million (350 TB) Chinese non-fiction collection ... which is bigger than Library Genesis. https://annas-archive.org/blog/duxiu-exclusive.html

Yes it means they will never release their dataset :(

Re: DeepSeek OCR

#93

Post by _vqpz »

ellisd wrote: post #36

The paper makes no mention of Anna’s Archive. I wouldn’t be surprised if DeepSeek took advantage of Anna’s offer granting OCR researchers access to their 7.5 million (350 TB) Chinese non-fiction collection ... which is bigger than Library Genesis. https://annas-archive.org/blog/duxiu-exclusive.html

Why do they need to grant access for people to use copies of books they don’t own?

Re: DeepSeek OCR

#94

Post by rsolva »

2big2fail_47 wrote: post #80

I find it interesting that there's all these independent AI-OCR Projects but still no commercial offering. Is it still too inaccurate, too complex or simply too expensive?

Mistral offers their OCR commercially through their API and in their Chat services, at least.

https://mistral.ai/news/mistral-ocr

Re: DeepSeek OCR

#95

Post by rco8786 »

miki123211 wrote: post #87
krackers wrote: post #8

The paper is more interesting than just another VLM for OCR, they start talking about compression and stuff. E.g. there is this quote >Our work represents an initial exploration into the boundaries of vision-text compression, investigating how many vision tokens are required to decode text tokens. The preliminary results are encouraging: DeepSeek-OCR achieves near-lossless OCR compression at approximately 10× ratios,…

Text tokens are quantized and represent subword units, vision tokens only exist in the embedding space. The way text tokenization works in LLMs is that you have a "lookup table" of (small) token ids to (large) vector embeddings. To pass text to the LLM, you split it at token boundaries, convert strings to token ids, and then construct the "context", a matrix where each row is a vector taken from that lookup table. Tr…

Great explanation, thanks. I was surprised to hear that models still only work with ~100k tokens, but after giving it some thought it makes sense. There's only so many words/subword units that get used in any given language. The entropy comes from all the billions of different ways those subwords can be ordered.

Re: DeepSeek OCR

#96

Post by tinyhouse »

OCR is not a great name for these models. While they can do traditional OCR such as digitize and scanned PDF for example, they do so much more.

Re: DeepSeek OCR

#97

Post by fxtentacle »

f33d5173 wrote: post #20
krackers wrote: post #11

Earlier quoted context omitted.

But naively wouldn't you expect the representation of a piece of text in terms of vision tokens to be roughly the same number of bits (or more) than the representation as textual token? You're changing representation sure, but that by itself doesn't give you any compute advantages unless there is some sparsity/compressability you can take advantage of in the domain you transform to right? So I guess my question is wh…

Vision is how humans see text. So text must have built in adaptations to protect from visual noise. For example, two words that look similar must never appear in similar contexts, or else they would be conflated. Hence we can safely reduce such words to the same token. Or something like that.

That also works purely on text and it's the trick I used in my German speech recognition engine ( https://arxiv.org/abs/2206.12693 ).

"I'm studying at Oxford Univ" has basically no loss in meaning even though "University" was truncated to less than half its characters.

Re: DeepSeek OCR

#98

Post by breadislove »

For everyone wondering how good this and other benchmarks are:

- the OmniAI benchmark is bad

- Instead check OmniDocBench[1] out

- Mistral OCR is far far behind most Open Source OCR models and even further behind then Gemini

- End to End OCR is still extremely tricky

- composed pipelines work better (layout detection -> reading order -> OCR every element)

- complex table parsing is still extremely difficult

[1]: https://github.com/opendatalab/OmniDocBench

Re: DeepSeek OCR

#99

Post by baobun »

pietz wrote: post #42

My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…

Chinese, especially handwritten.

Re: DeepSeek OCR

#100

Post by loaderchips »

Great work guys, how about we replace the global encoder with a Mamba (state-space) vision backbone to eliminate the O(n²) attention bottleneck, enabling linear-complexity encoding of high-resolution documents. Pair this with a non-autoregressive (Non-AR) decoder—such as Mask-Predict or iterative refinement—that generates all output tokens in parallel instead of sequentially. Together, this creates a fully parallelizable vision-to-text pipeline, The combination addresses both major bottlenecks in DeepSeek-OCR.
Post reply on HN