Papers › Anisotropic Convolutional Networks for 3D Semantic Scene Completion

Anisotropic Convolutional Networks for 3D Semantic Scene Completion

5 Apr 2020CVPR 2020 6arXiv:2004.02122archive 2025-07-28

Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan

As a voxel-wise labeling task, semantic scene completion (SSC) tries to simultaneously infer the occupancy and semantic labels for a scene from a single depth and/or RGB image. The key challenge for SSC is how to effectively take advantage of the 3D context to model various objects or stuffs with severe variations in shapes, layouts and visibility. To handle such variations, we propose a novel module called anisotropic convolution, which properties with flexibility and power impossible for the competing methods such as standard 3D convolution and some of its variations. In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely. The basic idea is to enable anisotropic 3D receptive field by decomposing a 3D convolution into three consecutive 1D convolutions, and the kernel size for each such 1D convolution is adaptively determined on the fly. By stacking multiple such anisotropic convolution modules, the voxel-wise modeling capability can be further enhanced while maintaining a controllable amount of model parameters. Extensive experiments on two SSC benchmarks, NYU-Depth-v2 and NYUCAD, show the superior performance of the proposed method. Our code is available at https://waterljwant.github.io/SSC/

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

waterljwant/SSC officialpytorch 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

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

Tasks

3D Semantic Scene Completion3D Semantic Scene Completion from a single RGB image

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Scene Completion NYUv2 AIC-Net mIoU 33.3 #13 of 28 Archive leaderboard report
3D Semantic Scene Completion from a single RGB image NYUv2 AICNet (rgb input - reported in MonoScene paper) mIoU 18.15 #5 of 6 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

3D ConvolutionConvolution

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