AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Diffusion-Based Contextual Reconstruction for Point Cloud Segmentation with Limited Annotations

Jiawei Lian, Zhengxue Wang, Wentao Qu, Haobo Jiang, Le Hui, Jian Yang

AAAI 2026 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the CGL module (local plus global guidance) to the diffusion framework (ablation)DiCoSeg · S3DIS Area5 (0.1% labels)mIoU: 64.2 -> 68.3Improved
add Local Context Aggregation to the guidance (ablation)DiCoSeg · S3DIS Area5 (0.1% labels)mIoU: 64.2 -> 67.4Improved
add Global Geometric Fusion to the guidance (ablation)DiCoSeg · S3DIS Area5 (0.1% labels)mIoU: 64.2 -> 66.9Improved
combine LCA and GGF rather than using either alone (ablation)DiCoSeg · ScanNetV2 val (0.1% labels)mIoU: 69.7 -> 70.7Improved
add the CGL module to the diffusion framework (ablation)DiCoSeg · ScanNetV2 val (0.1% labels)mIoU: 66.0 -> 70.7Improved
share only the decoder instead of sharing encoder and decoder (ablation)DiCoSeg · S3DIS Area5 (0.1% labels)mIoU: 64.3 -> 68.3Improved
share only the decoder instead of only the encoder (ablation)DiCoSeg · ScanNetV2 val (0.1% labels)mIoU: 65.6 -> 70.7Improved
add diffusion-based contextual reconstruction to SparseUNet under full supervisionSparseUNet · S3DIS Area5 (100% labels)mIoU: 65.4 -> 68.6Improved
use DiCoSeg instead of AADNet at very low label rateSemanticKITTI weak supervision · SemanticKITTI seq08 (0.1% labels)mIoU: 53.3 -> 62.6Improved
use DiCoSeg instead of PointCT at 0.1% labelsScanNetV2 weak supervision · ScanNetV2 val (0.1% labels)mIoU: 63.7 -> 70.3Improved
use DiCoSeg instead of PointCT at 0.1% labels on S3DISS3DIS weak supervision · S3DIS Area5 (0.1% labels)mIoU: 68.3 -> 68.3No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy