Pith. sign in

REVIEW 5 cited by

DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.18092 v3 pith:67KGJOM4 submitted 2024-09-26 cs.CV cs.AIcs.RO

Helin Cao , Sven Behnke This is my paper · ORCID
classification cs.CVcs.AIcs.RO
keywords lidarpointscenesemanticcloudsdenoisingdiffusionautonomous
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Perception systems play a crucial role in autonomous driving, incorporating multiple sensors and corresponding computer vision algorithms. 3D LiDAR sensors are widely used to capture sparse point clouds of the vehicle's surroundings. However, such systems struggle to perceive occluded areas and gaps in the scene due to the sparsity of these point clouds and their lack of semantics. To address these challenges, Semantic Scene Completion (SSC) jointly predicts unobserved geometry and semantics in the scene given raw LiDAR measurements, aiming for a more complete scene representation. Building on promising results of diffusion models in image generation and super-resolution tasks, we propose their extension to SSC by implementing the noising and denoising diffusion processes in the point and semantic spaces individually. To control the generation, we employ semantic LiDAR point clouds as conditional input and design local and global regularization losses to stabilize the denoising process. We evaluate our approach on autonomous driving datasets, and it achieves state-of-the-art performance for SSC, surpassing most existing methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A controlled LiDAR scene completion study finds that fixed-depth iterative refinement beats a parameter-matched wide model only for coherent missing regions, while training augmentation dominates for scattered thinning.

  2. OC-SOP: Enhancing Vision-Based 3D Semantic Occupancy Prediction by Object-Centric Awareness

    cs.CV 2025-06 conditional novelty 6.0 of 10

    OC-SOP fuses object detection queries into a semantic occupancy completion U-Net, improving foreground-object voxel accuracy and achieving state-of-the-art mIoU on SemanticKITTI.

  3. SWA-SOP: Spatially-aware Window Attention for Semantic Occupancy Prediction in Autonomous Driving

    cs.CV 2025-06 conditional novelty 6.0 of 10

    SWA-SOP shows that sliding-window attention with per-slot spatial embeddings and a center query improves semantic occupancy prediction on LiDAR and camera inputs, but the headline benchmark numbers are second-best rat...

  4. 3D and 4D World Modeling: A Survey

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A survey that defines 3D/4D world modeling, organizes methods into VideoGen, OccGen, and LiDARGen categories, and compiles datasets, metrics, and benchmark numbers.

  5. ${C}^{3}$-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting

    cs.CV 2025-08 conditional novelty 4.0 of 10

    C3-GS improves generalizable Gaussian Splatting by adding coordinate-aware attention, cross-dimensional attention, and cross-scale opacity fusion to the MVSGaussian baseline.

Pith tools