Papers › Two Stream 3D Semantic Scene Completion

Two Stream 3D Semantic Scene Completion

10 Apr 2018arXiv:1804.03550archive 2025-07-28

Martin Garbade, Yueh-Tung Chen, Johann Sawatzky, Juergen Gall

Inferring the 3D geometry and the semantic meaning of surfaces, which are occluded, is a very challenging task. Recently, a first end-to-end learning approach has been proposed that completes a scene from a single depth image. The approach voxelizes the scene and predicts for each voxel if it is occupied and, if it is occupied, the semantic class label. In this work, we propose a two stream approach that leverages depth information and semantic information, which is inferred from the RGB image, for this task. The approach constructs an incomplete 3D semantic tensor, which uses a compact three-channel encoding for the inferred semantic information, and uses a 3D CNN to infer the complete 3D semantic tensor. In our experimental evaluation, we show that the proposed two stream approach substantially outperforms the state-of-the-art for semantic scene completion.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

3D Semantic Scene Completion3D geometryVocal Bursts Valence Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Semantic Scene Completion NYUv2 TS3D mIoU 34.1 #11 of 28 Archive leaderboard report
3D Semantic Scene Completion SemanticKITTI TS3D+DNet+SATNet (Reported in SemanticKITTI dataset paper) mIoU 17.7 #8 of 20 Archive leaderboard report
3D Semantic Scene Completion SemanticKITTI TS3D+DNet (Reported in SemanticKITTI dataset paper) mIoU 10.2 #19 of 20 Archive leaderboard report
3D Semantic Scene Completion SemanticKITTI TS3D (Reported in SemanticKITTI dataset paper) mIoU 9.5 #20 of 20 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.

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