Papers › LiDPM: Rethinking Point Diffusion for Lidar Scene Completion

LiDPM: Rethinking Point Diffusion for Lidar Scene Completion

24 Apr 2025arXiv:2504.17791archive 2025-07-28

Tetiana Martyniuk, Gilles Puy, Alexandre Boulch, Renaud Marlet, Raoul de Charette

Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulation, show that they are not required to operate at the scene level, and that a vanilla DDPM with a well-chosen starting point is enough for completion. Finally, we demonstrate that our method, LiDPM, leads to better results in scene completion on SemanticKITTI. The project page is https://astra-vision.github.io/LiDPM .

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

astra-vision/LiDPM officialmentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps (arXiv:2206.00927; that paper's own run record: 17 ran (of which 2 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Lidar Scene Completion

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Lidar Scene Completion SemanticKITTI LiDPM (refined) Chamfer Distance 0.377 #2 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM (refined) JSD 3D 0.542 #2 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM (refined) JSD BEV 0.403 #2 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM (refined) Voxel IoU 0.1m 14.93 #2 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM (refined) Voxel IoU 0.2m 25.76 #2 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM (refined) Voxel IoU 0.5m 36.59 #2 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM Chamfer Distance 0.446 #4 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM JSD 3D 0.532 #4 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM JSD BEV 0.440 #4 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM Voxel IoU 0.1m 6.27 #4 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM Voxel IoU 0.2m 19.45 #4 of 4 Archive leaderboard report
Lidar Scene Completion SemanticKITTI LiDPM Voxel IoU 0.5m 34.09 #4 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