Papers › Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior

Edge-Aware 3D Instance Segmentation Network with Intelligent Semantic Prior

1 Jan 2024CVPR 2024 1archive 2025-07-28

Wonseok Roh, Hwanhee Jung, Giljoo Nam, Jinseop Yeom, Hyunje Park, Sang Ho Yoon, Sangpil Kim

While recent 3D instance segmentation approaches show promising results based on transformer architectures they often fail to correctly identify instances with similar appearances. They also ambiguously determine edges leading to multiple misclassifications of adjacent edge points. In this work we introduce a novel framework called EASE to overcome these challenges and improve the perception of complex 3D instances. We first propose a semantic guidance network to leverage rich semantic knowledge from a language model as intelligent priors enhancing the functional understanding of real-world instances beyond relying solely on geometrical information. We explicitly instruct the basic instance queries using text embeddings of each instance to learn deep semantic details. Further we utilize the edge prediction module encouraging the segmentation network to be edge-aware. We extract voxel-wise edge maps from point features and use them as auxiliary information for learning edge cues. In our extensive experiments on large-scale benchmarks ScanNetV2 ScanNet200 S3DIS and STPLS3D our EASE outperforms existing state-of-the-art models demonstrating its superior performance.

PaperPDF

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 Instance SegmentationInstance SegmentationLanguage ModelingLanguage ModellingSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Instance Segmentation STPLS3D EASE AP 64.5 #1 of 9 Archive leaderboard report
3D Instance Segmentation STPLS3D EASE AP25 86.9 #1 of 9 Archive leaderboard report
3D Instance Segmentation STPLS3D EASE AP50 80.8 #1 of 9 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