Papers › Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion

Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion

20 Mar 2024CVPR 2024 1arXiv:2403.13470archive 2025-07-28

Lucas Nunes, Rodrigo Marcuzzi, Benedikt Mersch, Jens Behley, Cyrill Stachniss

Computer vision techniques play a central role in the perception stack of autonomous vehicles. Such methods are employed to perceive the vehicle surroundings given sensor data. 3D LiDAR sensors are commonly used to collect sparse 3D point clouds from the scene. However, compared to human perception, such systems struggle to deduce the unseen parts of the scene given those sparse point clouds. In this matter, the scene completion task aims at predicting the gaps in the LiDAR measurements to achieve a more complete scene representation. Given the promising results of recent diffusion models as generative models for images, we propose extending them to achieve scene completion from a single 3D LiDAR scan. Previous works used diffusion models over range images extracted from LiDAR data, directly applying image-based diffusion methods. Distinctly, we propose to directly operate on the points, reformulating the noising and denoising diffusion process such that it can efficiently work at scene scale. Together with our approach, we propose a regularization loss to stabilize the noise predicted during the denoising process. Our experimental evaluation shows that our method can complete the scene given a single LiDAR scan as input, producing a scene with more details compared to state-of-the-art scene completion methods. We believe that our proposed diffusion process formulation can support further research in diffusion models applied to scene-scale point cloud data.

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="2403.13470")

Code

Syntology Ran 4 of 6 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

prbonn/lidiff officialmentioned in paperpytorchMIT 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

6 samples harvested; 4 ran; 0 honoured the contract we drafted; 2 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.

4ran
2unverified

Licence: 0 of the 6 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 prbonn/lidiff. “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.

feats_to_coord prbonn/lidiff/lidiff/utils/collations.py official repository ran MIT (permissive) · 273dcb9efc924348 · report
histogram_point_cloud prbonn/lidiff/lidiff/utils/histogram_metrics.py official repository ran MIT (permissive) · 00586b29e0113f0b · report
normalize_pcd prbonn/lidiff/lidiff/utils/collations.py official repository ran MIT (permissive) · 8823481d17172a2c · report
unormalize_pcd prbonn/lidiff/lidiff/utils/collations.py official repository ran MIT (permissive) · b04f5d8053dc9422 · report
load_poses prbonn/lidiff/lidiff/map_from_scans.py official repository unverified MIT (permissive) · 21cd8e2f060ce50c · report
parse_calibration prbonn/lidiff/lidiff/map_from_scans.py official repository unverified MIT (permissive) · b39e1616e4146e48 · report

Tasks

Autonomous VehiclesDenoisingLidar Scene Completion

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lidar Scene Completion SemanticKITTI LiDiff (refined) Chamfer Distance 0.376 #1 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff (refined) JSD 3D 0.573 #1 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff (refined) JSD BEV 0.416 #1 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff (refined) Voxel IoU 0.1m 13.40 #1 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff (refined) Voxel IoU 0.2m 22.99 #1 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff (refined) Voxel IoU 0.5m 32.43 #1 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff Chamfer Distance 0.434 #3 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff JSD 3D 0.564 #3 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff JSD BEV 0.444 #3 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff Voxel IoU 0.1m 4.67 #3 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff Voxel IoU 0.2m 16.79 #3 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDiff Voxel IoU 0.5m 31.47 #3 of 4 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