Papers › TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

28 Mar 2024arXiv:2403.19589archive 2025-07-28

Bu Jin, Yupeng Zheng, Pengfei Li, Weize Li, Yuhang Zheng, Sujie Hu, Xinyu Liu, Jinwei Zhu, Zhijie Yan, Haiyang Sun, Kun Zhan, Peng Jia, Xiaoxiao Long, Yilun Chen, Hao Zhao

3D dense captioning stands as a cornerstone in achieving a comprehensive understanding of 3D scenes through natural language. It has recently witnessed remarkable achievements, particularly in indoor settings. However, the exploration of 3D dense captioning in outdoor scenes is hindered by two major challenges: 1) the domain gap between indoor and outdoor scenes, such as dynamics and sparse visual inputs, makes it difficult to directly adapt existing indoor methods; 2) the lack of data with comprehensive box-caption pair annotations specifically tailored for outdoor scenes. To this end, we introduce the new task of outdoor 3D dense captioning. As input, we assume a LiDAR point cloud and a set of RGB images captured by the panoramic camera rig. The expected output is a set of object boxes with captions. To tackle this task, we propose the TOD3Cap network, which leverages the BEV representation to generate object box proposals and integrates Relation Q-Former with LLaMA-Adapter to generate rich captions for these objects. We also introduce the TOD3Cap dataset, the largest one to our knowledge for 3D dense captioning in outdoor scenes, which contains 2.3M descriptions of 64.3K outdoor objects from 850 scenes. Notably, our TOD3Cap network can effectively localize and caption 3D objects in outdoor scenes, which outperforms baseline methods by a significant margin (+9.6 CiDEr@0.5IoU). Code, data, and models are publicly available at https://github.com/jxbbb/TOD3Cap.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2403.19589")

Code

Syntology Ran 10 of 16 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 16 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jxbbb/tod3cap officialmentioned in papermentioned on GitHubpytorch 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

16 samples harvested; 10 ran; 1 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
2ran · fixture could not drive it
5ran
6unverified

Licence: 16 of the 16 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 jxbbb/tod3cap. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

adjust_learning_rate jxbbb/tod3cap/tod3cap_camera/util/lr_sched.py official repository ran · honoured contract no licence file found · pointer only · bd3578806ecf5ac2 · report
all_reduce_mean jxbbb/tod3cap/tod3cap_camera/util/misc.py official repository ran fingerprinted no licence file found · pointer only · fdb1265b615d25b9 · report
apply_rotary_emb jxbbb/tod3cap/tod3cap_camera/llama/llama.py official repository ran · fixture could not drive it no licence file found · pointer only · b47d48e431b34acd · report
format_prompt jxbbb/tod3cap/tod3cap_camera/llama/utils.py official repository ran fingerprinted no licence file found · pointer only · 7006a7479b6f348f · report
position_embedding jxbbb/tod3cap/tod3cap_camera/llama/GPT2.py official repository ran fingerprinted no licence file found · pointer only · de80f1711a0ddf21 · report
position_embedding jxbbb/tod3cap/tod3cap_camera/llama/llama_adapter_gpt.py official repository ran fingerprinted no licence file found · pointer only · a247fcd78818b192 · report
precompute_freqs_cis jxbbb/tod3cap/tod3cap_camera/llama/llama.py official repository ran · violated contract no licence file found · pointer only · 14a84c2cbfebc413 · report
process_checkpoint jxbbb/tod3cap/tod3cap_camera/mmdetection3d/.dev_scripts/gather_models.py official repository ran no licence file found · pointer only · e76a491553cf9fcf · report
reshape_for_broadcast jxbbb/tod3cap/tod3cap_camera/llama/llama.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 70bf6ebaafd266c4 · report
sample_top_p jxbbb/tod3cap/tod3cap_camera/llama/utils.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 8845976729f4c4ee · report
add_weight_decay jxbbb/tod3cap/tod3cap_camera/util/misc.py official repository unverified no licence file found · pointer only · b40701674badc944 · report
get_final_epoch jxbbb/tod3cap/tod3cap_camera/mmdetection3d/.dev_scripts/gather_models.py official repository unverified no licence file found · pointer only · 90f6ae7209cde36f · report
get_model_dataset jxbbb/tod3cap/tod3cap_camera/mmdetection3d/.dev_scripts/gather_models.py official repository unverified no licence file found · pointer only · da059252c88ecf40 · report
load jxbbb/tod3cap/tod3cap_camera/llama/llama_adapter.py official repository unverified no licence file found · pointer only · 825615e23fa39149 · report
load jxbbb/tod3cap/tod3cap_camera/llama/llama_adapter_back.py official repository unverified no licence file found · pointer only · 16bd604b0433607b · report
token_llama2gpt2 jxbbb/tod3cap/tod3cap_camera/llama/GPT2.py official repository unverified no licence file found · pointer only · ca22408e380b541a · report

Tasks

3D dense captioningDense Captioning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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