AI Paper Atlas

Research map / 3D vision / 3D generation

InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes

Zesong Yang, Bangbang Yang, Wenqi Dong, Chenxuan Cao, Liyuan Cui, Yuewen Ma, Zhaopeng Cui, Hujun Bao

ICCV 2025 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 7 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 filtered intra-view 2D masks to contrastive learning on 3D masks (ablation)InstaScene spatial contrastive learning · LERF-Mask (average)mIoU (%): 79.0 -> 83.6Improved
add cross-view 2D masks on top of filtered 2D masks (ablation)InstaScene spatial contrastive learning · LERF-Mask (average)mIoU (%): 83.6 -> 85.6Improved
use 3D mask guidance with filtered and cross-view masks instead of raw noisy 2D masks (ablation)InstaScene · LERF-Mask (average)mIoU (%): 80.5 -> 85.6Improved
use coarse 3D masks alone instead of noisy 2D masks (ablation)InstaScene · LERF-Mask (average)mIoU (%): 80.5 -> 79.0Hurt
InstaScene versus LangSplat and GSGrouping for instance segmentationInstaScene · LERF-Mask (average)mIoU (%): 60.6 -> 85.6Improved
in-situ generation versus SpaRP multi-view completionInstaScene · Replica-CAD instance completionVolume IoU: 0.590 -> 0.716Improved
in-situ generation versus original 2DGS reconstruction on unknown viewsInstaScene · Replica-CAD instance completionPSNR (unknown views): 27.44 -> 29.02Improved
in-situ generation versus 2DGS on Chamfer DistanceInstaScene · Replica-CAD instance completionChamfer Distance: 0.028 -> 0.016Improved
alternate conditioning views instead of single-view conditioning (ablation)InstaScene in-situ generation · ZipNeRF / Replica-CAD (qualitative)visual qualityImproved
add geometry-aware warped feature conditioning to alternated views (ablation)InstaScene in-situ generation · ZipNeRF / Replica-CAD (qualitative)visual qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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