Papers › Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors

Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors

26 Nov 2019CVPR 2020 6arXiv:1911.11288archive 2025-07-28

Sergey Zakharov, Wadim Kehl, Arjun Bhargava, Adrien Gaidon

We present an automatic annotation pipeline to recover 9D cuboids and 3D shapes from pre-trained off-the-shelf 2D detectors and sparse LIDAR data. Our autolabeling method solves an ill-posed inverse problem by considering learned shape priors and optimizing geometric and physical parameters. To address this challenging problem, we apply a novel differentiable shape renderer to signed distance fields (SDF), leveraged together with normalized object coordinate spaces (NOCS). Initially trained on synthetic data to predict shape and coordinates, our method uses these predictions for projective and geometric alignment over real samples. Moreover, we also propose a curriculum learning strategy, iteratively retraining on samples of increasing difficulty in subsequent self-improving annotation rounds. Our experiments on the KITTI3D dataset show that we can recover a substantial amount of accurate cuboids, and that these autolabels can be used to train 3D vehicle detectors with state-of-the-art results.

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="1911.11288")

Code

Syntology Ran 2 of 7 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 7 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.

TRI-ML/sdflabel officialmentioned 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

7 samples harvested; 2 ran; 0 honoured the contract we drafted; 5 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 · our draft was wrong
1ran
5unverified

Licence: 0 of the 7 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 TRI-ML/sdflabel. “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.

conv3x3 TRI-ML/sdflabel/networks/resnet_css.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
div_up TRI-ML/sdflabel/pipelines/rotate_iou.py official repository ran fingerprinted MIT (permissive) · 20fbfa2279e1ce4b · report
angle_diff TRI-ML/sdflabel/pipelines/detection_3d.py official repository unverified MIT (permissive) · 5197730ac2ae824d · report
clean_kitti_data TRI-ML/sdflabel/pipelines/detection_3d.py official repository unverified MIT (permissive) · eb9d14c02ecd4d53 · report
difficulty_by_distance TRI-ML/sdflabel/pipelines/detection_3d.py official repository unverified MIT (permissive) · 698e95c7418b29f5 · report
get_opt_params TRI-ML/sdflabel/pipelines/optimizer.py official repository unverified MIT (permissive) · f7535f157ec32dc2 · report
project_vecs_onto_sphere TRI-ML/sdflabel/networks/resnet_css.py official repository unverified MIT (permissive) · af2b40fd6da62cf6 · report

Tasks

Weakly Supervised 3D Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly Supervised 3D Detection KITTI-360 Auto-Labels mAP@0.3 48.16 #2 of 3 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.

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