Papers › Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement

10 Mar 2022CVPR 2022 1arXiv:2203.05238archive 2025-07-28

Xiuwei Xu, Yifan Wang, Yu Zheng, Yongming Rao, Jie zhou, Jiwen Lu

In this paper, we propose a weakly-supervised approach for 3D object detection, which makes it possible to train a strong 3D detector with position-level annotations (i.e. annotations of object centers). In order to remedy the information loss from box annotations to centers, our method, namely Back to Reality (BR), makes use of synthetic 3D shapes to convert the weak labels into fully-annotated virtual scenes as stronger supervision, and in turn utilizes the perfect virtual labels to complement and refine the real labels. Specifically, we first assemble 3D shapes into physically reasonable virtual scenes according to the coarse scene layout extracted from position-level annotations. Then we go back to reality by applying a virtual-to-real domain adaptation method, which refine the weak labels and additionally supervise the training of detector with the virtual scenes. Furthermore, we propose a more challenging benckmark for indoor 3D object detection with more diversity in object sizes to better show the potential of BR. With less than 5% of the labeling labor, we achieve comparable detection performance with some popular fully-supervised approaches on the widely used ScanNet dataset. Code is available at: https://github.com/wyf-ACCEPT/BackToReality

PaperPDFConference PDFCodeCode 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="2203.05238")

Code

Syntology Ran 7 of 25 code samples harvested from 2 repositories linked to this paper; 18 have no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 25 samples from 2 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

wyf-accept/backtoreality officialmentioned in papermentioned on GitHubpytorchMIT report
xuxw98/backtoreality 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

25 samples harvested; 7 ran; 2 honoured the contract we drafted; 18 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 · honoured contract
3ran · our draft was wrong
1ran · fixture could not drive it
1ran
18unverified

Licence: 0 of the 25 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

SigmoidFocalClassificationLoss xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository ran MIT (permissive) · 2616a152109ab293 · report
compute_objectness_loss_based_on_query_points xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository ran · fixture could not drive it MIT (permissive) · 642ad5f6031a8aa1 · report
compute_points_obj_cls_loss_hard_topk xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository ran · honoured contract MIT (permissive) · c9e3c6528cd69995 · report
compute_points_obj_cls_loss_hard_topk_weak xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository ran · honoured contract MIT (permissive) · 5d501aaa66769592 · report
l1_loss xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · e1e4a142a595bcf2 · report
nn_distance xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository ran · our draft was wrong MIT (permissive) · 60f5b7fe1cc54f17 · report
smoothl1_loss xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · a18fa7b4ad55d938 · report
Is_horizontal wyf-ACCEPT/BackToReality/data_generation/ScanNet/segment_tools.py official repository unverified MIT (permissive) · af68a34722851d0e · report
compute_box_and_sem_cls_loss xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository unverified MIT (permissive) · 7d9d44a980e24c22 · report
compute_center_and_sem_cls_loss xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository unverified MIT (permissive) · 4a436f36baabf7ee · report
compute_objectness_loss_based_on_query_points_weak xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository unverified MIT (permissive) · 137a1dae05a132ca · report
find_nearest_object wyf-ACCEPT/BackToReality/data_generation/ScanNet/scannet_scene_synthesis.py official repository unverified MIT (permissive) · cc8c7c54286373af · report
get_MER wyf-ACCEPT/BackToReality/data_generation/Matterport3D/modelnet40_tools.py official repository unverified MIT (permissive) · 5909c81367fe7e2b · report
get_MER wyf-ACCEPT/BackToReality/data_generation/Matterport3D/matterport_scene_synthesis.py official repository unverified MIT (permissive) · f66ccab4c6f93ada · report
get_id_to_label wyf-ACCEPT/BackToReality/data_generation/ScanNet/ins_ply.py official repository unverified MIT (permissive) · 114d8fa311c666a5 · report
get_loss_weak xuxw98/backtoreality/detection/GroupFree3D/models/loss_helper.py official repository unverified MIT (permissive) · a8c59f9640373662 · report
get_normal wyf-ACCEPT/BackToReality/data_generation/ScanNet/segment_tools.py official repository unverified MIT (permissive) · 52dc1aebbd2b533c · report
get_solid_MER wyf-ACCEPT/BackToReality/data_generation/ScanNet/scannet_scene_synthesis.py official repository unverified MIT (permissive) · 22667864de7fcab8 · report
get_solid_MER wyf-ACCEPT/BackToReality/data_generation/Matterport3D/matterport_scene_synthesis.py official repository unverified MIT (permissive) · d7006f63008a044b · report
get_support_z wyf-ACCEPT/BackToReality/data_generation/Matterport3D/modelnet40_tools.py official repository unverified MIT (permissive) · d9e542fd2784b3d8 · report
modelnet40_to_id wyf-ACCEPT/BackToReality/data_generation/ScanNet/scannet_utils.py official repository unverified MIT (permissive) · fde3fc16b0a466d2 · report
read_aggregation wyf-ACCEPT/BackToReality/data_generation/ScanNet/ins_ply.py official repository unverified MIT (permissive) · 99136f050d5a159b · report
read_label_mapping wyf-ACCEPT/BackToReality/data_generation/ScanNet/scannet_utils.py official repository unverified MIT (permissive) · 69e7d6553f196430 · report
read_mesh_vertices wyf-ACCEPT/BackToReality/data_generation/ScanNet/scannet_utils.py official repository unverified MIT (permissive) · f772d38e5bc06661 · report
read_segmentation wyf-ACCEPT/BackToReality/data_generation/ScanNet/ins_ply.py official repository unverified MIT (permissive) · 527894e637039fb3 · report

Tasks

3D Object DetectionDiversityDomain AdaptationObjectObject Detectionobject-detection

1 archive task tag without a task page not shown.

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