AI Paper Atlas

Research map / 3D vision / 3D generation

ASSIST-3D: Adapted Scene Synthesis for Class-Agnostic 3D Instance Segmentation

Shengchao Zhou, Jiehong Lin, Jiahui Liu, Shizhen Zhao, Chirui Chang, Xiaojuan Qi

AAAI 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 0 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 ASSIST-3D synthetic data to ScanNetV2 trainingMask3D · ScanNet++AP: 12.0 -> 22.2Improved
add ASSIST-3D synthetic data to ScanNetV2 trainingMask3D · S3DISAP: 13.6 -> 29.0Improved
add ASSIST-3D synthetic data to ScanNetV2 trainingMask3D · ScanNetV2 valAP: 46.6 -> 48.1Improved
increase number of object geometry clusters used for synthesis from 1 to 5 (ablation)ASSIST-3D · ScanNet++AP: 14.6 -> 22.2Improved
increase geometry clusters from 1 to 5 (ablation)ASSIST-3D · ScanNet++ (out-of-domain objects)AR: 3.2 -> 12.4Improved
lower co-occurrence enforcement (100% to 0%) to raise context complexity (ablation)ASSIST-3D · ScanNet++AP: 17.2 -> 22.2Improved
use rendering-based point cloud construction instead of mesh sampling (ablation)ASSIST-3D · S3DISAP: 18.8 -> 29.0Improved
use ASSIST-3D scene layout/selection instead of Holodeck data (ablation)Mask3D · ScanNet++AP: 14.2 -> 22.2Improved
use reasonable layouts (ASSIST-3D) instead of RandomRooms random placement (ablation)Mask3D · S3DISAP: 23.5 -> 29.0Improved
scale number of synthetic scenes and object classes (ablation)ASSIST-3D · ScanNet++ and S3DISAPImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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