SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.08885 · 2024

SLCF-Net: Sequential LiDAR-Camera Fusion for Semantic Scene Completion using a 3D Recurrent U-Net

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
helincao618/SLCF-Net canonical 2 of 5
FunctionStatusWhere it lives
CE_ssc_loss Ran helincao618/SLCF-Net/slcfnet/loss/ssc_loss.py
code served (permissive licence) · get_code("2a08bb56d2b6ea62")
compute_super_CP_multilabel_loss Ran helincao618/SLCF-Net/slcfnet/loss/CRP_loss.py
code served (permissive licence) · get_code("5530781a69d17464")
KL_sep Not yet run helincao618/SLCF-Net/slcfnet/loss/ssc_loss.py
code served (permissive licence) · get_code("033da7a511cc1166")
extract_features Not yet run helincao618/SLCF-Net/slcfnet/models/modules.py
code served (permissive licence) · get_code("7210b5f5a141b06d")
geo_scal_loss Not yet run helincao618/SLCF-Net/slcfnet/loss/ssc_loss.py
code served (permissive licence) · get_code("1cf8e8cd991e96bb")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We introduce SLCF-Net, a novel approach for the Semantic Scene Completion (SSC) task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. The images are semantically segmented by a pre-trained 2D U-Net and a dense depth prior is estimated from a depth-conditioned pipeline fueled by Depth Anything. To associate the 2D image features with the 3D scene volume, we introduce Gaussian-decay Depth-prior Projection (GDP). This module projects the 2D features into the 3D volume along the line of sight with a Gaussian-decay function, centered around the depth prior. Volumetric semantics is computed by a 3D U-Net. We propagate the hidden 3D U-Net state using the sensor motion and design a novel loss to ensure temporal consistency. We evaluate our approach on the SemanticKITTI dataset and compare it with leading SSC approaches. The SLCF-Net excels in all SSC metrics and shows great temporal consistency.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.08885")
get_code_for_paper("2403.08885")
have("2403.08885")

Connect an agent — have() is free.