Papers › 4D Panoptic Scene Graph Generation

4D Panoptic Scene Graph Generation

16 May 2024NeurIPS 2023 11arXiv:2405.10305archive 2025-07-28

Jingkang Yang, Jun Cen, Wenxuan Peng, Shuai Liu, Fangzhou Hong, Xiangtai Li, Kaiyang Zhou, Qifeng Chen, Ziwei Liu

We are living in a three-dimensional space while moving forward through a fourth dimension: time. To allow artificial intelligence to develop a comprehensive understanding of such a 4D environment, we introduce 4D Panoptic Scene Graph (PSG-4D), a new representation that bridges the raw visual data perceived in a dynamic 4D world and high-level visual understanding. Specifically, PSG-4D abstracts rich 4D sensory data into nodes, which represent entities with precise location and status information, and edges, which capture the temporal relations. To facilitate research in this new area, we build a richly annotated PSG-4D dataset consisting of 3K RGB-D videos with a total of 1M frames, each of which is labeled with 4D panoptic segmentation masks as well as fine-grained, dynamic scene graphs. To solve PSG-4D, we propose PSG4DFormer, a Transformer-based model that can predict panoptic segmentation masks, track masks along the time axis, and generate the corresponding scene graphs via a relation component. Extensive experiments on the new dataset show that our method can serve as a strong baseline for future research on PSG-4D. In the end, we provide a real-world application example to demonstrate how we can achieve dynamic scene understanding by integrating a large language model into our PSG-4D system.

PaperPDFConference PDFCodeCode 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

Syntology 14 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 3 repositories, 13 ran (9 with no instrument failure; 4 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 13 samples that ran have no recorded date.

jingkang50/psg4d officialmentioned in papermentioned on GitHubpytorchSyntology: 9 samples, 8 ran (4 instrument-failed) · 1 unverified report
Jingkang50/OpenPSG officialmentioned in paperpytorchMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
jingkang50/openpvsg officialmentioned in paperpytorchNOASSERTIONSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 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

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
5ran
1unverified

Licence: 10 of the 14 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

jingkang50/psg4d official repository 9 samples, 8 ran (4 instrument-failed) · 1 unverified
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
pc_seg/backbone/transformer.py ran no licence file found · pointer only · 6693fd4e3fbcd72f · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, d_k:int/0/int, mask:Tensor/4/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-24
compute_vn pc_seg/lib/segmentator/utils.py ran · honoured contract no licence file found · pointer only · 9a93ecf3e946d063 · report fixture: signature mesh:MockMesh/0/? · returned ndarray · level recorded 2026-09-24
compute_vn_kernel pc_seg/lib/segmentator/utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 361f4cf883997964 · report fixture: signature vertices:ndarray/2/float, faces:ndarray/2/int · returned ndarray · level recorded 2026-09-24
get_clones in 39 papers pc_seg/backbone/transformer.py ran · our draft was wrong no licence file found · pointer only · 891b8ebab395921f · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
initialize_optimizer in 6 papers pc_seg/utils/solver.py ran no licence file found · pointer only · 4c158fc0e48afd02 · report fixture: signature params:generator/0/?, config:Config/0/? · returned Adam · level recorded 2026-09-24
initialize_scheduler in 6 papers pc_seg/utils/solver.py ran no licence file found · pointer only · 521ea446997228b2 · report fixture: signature optimizer:SGD/0/?, config:Config/0/?, last_step:int/0/int · returned PolyLR · level recorded 2026-09-24
joint_stracks in 8 papers pc_track/unitrack/basetrack.py ran · our draft was wrong no licence file found · pointer only · 1360e4a605aad164 · report fixture: signature tlista:list/1/Track, tlistb:list/1/Track · returned list · level recorded, date not recorded
sub_stracks in 8 papers pc_track/unitrack/basetrack.py ran · our draft was wrong no licence file found · pointer only · 30a3c33b9572d851 · report fixture: signature tlista:list/1/STrack, tlistb:list/1/STrack · returned list · level recorded, date not recorded
remove_duplicate_stracks pc_track/unitrack/basetrack.py unverified no licence file found · pointer only · c9470c4dd1975f70 · report
Jingkang50/OpenPSG official repository 4 samples, 4 ran (0 instrument-failed) · 0 unverified
argsort_desc in 6 papers openpsg/evaluation/sgg_eval_util.py ran · honoured contract fingerprinted MIT (permissive) · f4c6fd89f0168001 · report fixture: signature scores:ndarray/2/float · returned ndarray · level recorded 2026-09-24
format_result_dict openpsg/evaluation/sgg_eval.py ran MIT (permissive) · f4c579a3b51908a0 · report fixture: signature result_dict:dict/0/?, result_str:str/0/str, mode:str/0/str · returned dict · level recorded 2026-09-24
intersect_2d in 7 papers openpsg/evaluation/sgg_eval_util.py ran · violated contract MIT (permissive) · c3e5199833bfb97a · report fixture: returned ndarray · level recorded 2026-09-24
mask_iou openpsg/evaluation/sgg_metrics.py ran · honoured contract MIT (permissive) · 0df7ff0ca2d84435 · report fixture: signature mask1:ndarray/2/bool, mask2:ndarray/2/bool · returned float64 · level recorded 2026-09-24
jingkang50/openpvsg official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
preprocess_panoptic_gt_split_th_st models/mask2former/mask2former_head_split_focal.py ran licence not identified · pointer only · 9fc317bb1ed0030e · report fixture: signature gt_labels:Tensor/1/int, gt_masks:BitmapMasks/0/?, gt_semantic_seg:Tensor/3/int, num_things:int/0/int, num_stuff:int/0/int, img_metas:dict/0/? · returned tuple · level recorded 2026-09-24

Tasks

4D Panoptic SegmentationGraph GenerationLanguage ModellingLarge Language ModelPanoptic Scene Graph GenerationPanoptic SegmentationScene Graph GenerationScene Understanding

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