Papers › Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding

Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding

5 Sep 2024arXiv:2409.03757archive 2025-07-28

Yunze Man, Shuhong Zheng, Zhipeng Bao, Martial Hebert, Liang-Yan Gui, Yu-Xiong Wang

Complex 3D scene understanding has gained increasing attention, with scene encoding strategies playing a crucial role in this success. However, the optimal scene encoding strategies for various scenarios remain unclear, particularly compared to their image-based counterparts. To address this issue, we present a comprehensive study that probes various visual encoding models for 3D scene understanding, identifying the strengths and limitations of each model across different scenarios. Our evaluation spans seven vision foundation encoders, including image-based, video-based, and 3D foundation models. We evaluate these models in four tasks: Vision-Language Scene Reasoning, Visual Grounding, Segmentation, and Registration, each focusing on different aspects of scene understanding. Our evaluations yield key findings: DINOv2 demonstrates superior performance, video models excel in object-level tasks, diffusion models benefit geometric tasks, and language-pretrained models show unexpected limitations in language-related tasks. These insights challenge some conventional understandings, provide novel perspectives on leveraging visual foundation models, and highlight the need for more flexible encoder selection in future vision-language and scene-understanding tasks. Code: https://github.com/YunzeMan/Lexicon3D

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="2409.03757")

Code

Syntology Ran 2 of 9 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: named in the paper: 9 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yunzeman/lexicon3d mentioned in papermentioned on GitHubpytorchMIT 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

9 samples harvested; 2 ran; 0 honoured the contract we drafted; 7 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.

2ran
7unverified

Licence: 0 of the 9 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 yunzeman/lexicon3d. “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_intrinsic yunzeman/lexicon3d/lexicon3d/fusion_util.py named in the paper ran MIT (permissive) · c58cf40ab0e3d808 · report
make_intrinsic yunzeman/lexicon3d/lexicon3d/fusion_util.py named in the paper ran MIT (permissive) · 6385efe2f5a14a24 · report
extract_lseg_img_feature yunzeman/lexicon3d/lexicon3d/fusion_util.py named in the paper unverified MIT (permissive) · 6d3d570ec9c749ac · report
measure_inference_time yunzeman/lexicon3d/lexicon3d/evaluate_complexity.py named in the paper unverified MIT (permissive) · d75e167c843e048a · report
measure_memory yunzeman/lexicon3d/lexicon3d/evaluate_complexity.py named in the paper unverified MIT (permissive) · 3f9caaede747a476 · report
module_inference yunzeman/lexicon3d/lexicon3d/models.py named in the paper unverified MIT (permissive) · 68cce1e838d6d71a · report
pad_image yunzeman/lexicon3d/lexicon3d/models.py named in the paper unverified MIT (permissive) · 28ad88e75cdc78c6 · report
resize_image yunzeman/lexicon3d/lexicon3d/models.py named in the paper unverified MIT (permissive) · 2a9ddb0649c62fe4 · report
run_model yunzeman/lexicon3d/lexicon3d/evaluate_complexity.py named in the paper unverified MIT (permissive) · 0781f631b94b8147 · report

Tasks

Question AnsweringScene UnderstandingVisual Grounding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering SQA3D Lexicon3D AnswerExactMatch (Question Answering) 50.7 #3 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

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