Papers › ImageInWords: Unlocking Hyper-Detailed Image Descriptions

ImageInWords: Unlocking Hyper-Detailed Image Descriptions

5 May 2024arXiv:2405.02793archive 2025-07-28

Roopal Garg, Andrea Burns, Burcu Karagol Ayan, Yonatan Bitton, Ceslee Montgomery, Yasumasa Onoe, Andrew Bunner, Ranjay Krishna, Jason Baldridge, Radu Soricut

Despite the longstanding adage "an image is worth a thousand words," generating accurate hyper-detailed image descriptions remains unsolved. Trained on short web-scraped image text, vision-language models often generate incomplete descriptions with visual inconsistencies. We address this via a novel data-centric approach with ImageInWords (IIW), a carefully designed human-in-the-loop framework for curating hyper-detailed image descriptions. Human evaluations on IIW data show major gains compared to recent datasets (+66%) and GPT4V (+48%) across comprehensiveness, specificity, hallucinations, and more. We also show that fine-tuning with IIW data improves these metrics by +31% against models trained with prior work, even with only 9k samples. Lastly, we evaluate IIW models with text-to-image generation and vision-language reasoning tasks. Our generated descriptions result in the highest fidelity images, and boost compositional reasoning by up to 6% on ARO, SVO-Probes, and Winoground datasets. We release the IIW Eval benchmark with human judgement labels, object and image-level annotations from our framework, and existing image caption datasets enriched via IIW-model.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (google/imageinwords) was not harvested; the 10 samples below come from 1 community repository.

Syntology 10 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 10 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google/imageinwords officialmentioned in papermentioned on GitHubSyntology: not harvested report
google-deepmind/proactive_t2i_agents mentioned on GitHubApache-2.0Syntology: 10 samples, 8 ran (0 instrument-failed) · 2 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran
2unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from google-deepmind/proactive_t2i_agents. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

google-deepmind/proactive_t2i_agents community (archive-listed) 10 samples, 8 ran (0 instrument-failed) · 2 unverified
entity_parser_prompt agent/prompts.py ran fingerprinted Apache-2.0 (permissive) · 6fdfee8ae85731ff · report fixture: signature user_prompt:str/0/str · returned str · level recorded 2026-09-24
entity_parser_prompt_w_background agent/prompts.py ran fingerprinted Apache-2.0 (permissive) · 96bd654b5fe8cafd · report fixture: signature user_prompt:str/0/str · returned str · level recorded 2026-09-24
entropy in 112 papers
census: 22 implementations from 25 papers, 16 distinct outputs across 4 buckets, one shared input per bucket
agent/agent_classes.py ran fingerprinted Apache-2.0 (permissive) · ac24c3867c0d6c29 · report fixture: signature probs:list/1/float · returned float64 · level recorded 2026-09-24
is_confident agent/belief_utils.py ran Apache-2.0 (permissive) · 4337cf11cd0ec49c · report fixture: signature belief_state:BeliefState/0/?, confidence_threshold:float/0/float, importance_threshold:float/0/float · returned bool · level recorded 2026-09-24
load_img in 47 papers agent/image_utils.py ran Apache-2.0 (permissive) · 912864da44ac4f8d · report fixture: signature path:str/0/str · returned PngImageFile · level recorded 2026-09-24
merge_info_prompt agent/prompts.py ran fingerprinted Apache-2.0 (permissive) · 9969f5aeb6be4c91 · report fixture: signature prompt:str/0/str, additional_info:str/0/str · returned str · level recorded 2026-09-25
most_likely_deterministic_state agent/belief_utils.py ran Apache-2.0 (permissive) · 2d562b2e2b98bf22 · report fixture: signature belief_state:BeliefState/0/?, remove_uncertain_entities:bool/0/bool, remove_uncertain_attributes:bool/0/bool, prob_threshold:float/0/float · returned BeliefState · level recorded 2026-09-24
show_image in 6 papers agent/image_utils.py ran Apache-2.0 (permissive) · dce5b9144b3351bc · report fixture: signature image_pil:Image/0/? · returned AxesImage · level recorded 2026-09-24
get_image_description agent/image_utils.py unverified Apache-2.0 (permissive) · 7d93f6d7eb593350 · report
negative_log_likelihood in 6 papers agent/belief_metrics.py unverified Apache-2.0 (permissive) · b9dcd4f5f46998b9 · report

Tasks

Image GenerationSpecificityText to Image GenerationText-to-Image Generation

Datasets

Introduced by this paper, per the archive.

IIW-400

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections