AI Paper Atlas

Research map / 3D vision / 3D generation

I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners

Lu Ling, Yunhao Ge, Yichen Sheng, Aniket Bera

CVPR 2026 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 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 view-centric (VC) space (ablation)I-Scene · BlendSwap & ScenethesisF-Score-S: 79.12 -> 90.79Improved
add view-centric (VC) space (ablation)I-Scene · BlendSwap & ScenethesisCD-S: 0.0351 -> 0.0118Improved
add view-centric (VC) space (ablation)I-Scene · BlendSwap & ScenethesisIoU: 0.7557 -> 0.8222Improved
add view-centric (VC) space (ablation)I-Scene · 3D-FRONTIoU: 0.8598 -> 0.8792Improved
add non-semantic random scenes (NS) (ablation)I-Scene · BlendSwap & ScenethesisF-Score-O: 68.87 -> 72.39Improved
add non-semantic random scenes (NS) (ablation)I-Scene · 3D-FRONTF-Score-O: 81.34 -> 84.28Improved
add non-semantic random scenes (NS) (ablation)I-Scene · 3D-FRONTF-Score-S: 93.77 -> 93.50No clear effect
train on Rand-25K instead of 3D-FT (ablation)I-Scene · BlendSwap & ScenethesisF-Score-S: 90.79 -> 93.60Improved
train on Rand-25K instead of 3D-FT (ablation)I-Scene · 3D-FRONTIoU-B: 0.8792 -> 0.7783Hurt
scale random scenes from 15K to 25K (ablation)I-Scene · BlendSwap & ScenethesisF-Score-S: 92.67 -> 93.60Improved
mix 3D-FT with Rand-15K instead of 3D-FT only (ablation)I-Scene · BlendSwap & ScenethesisF-Score-S: 90.79 -> 94.26Improved
use I-Scene instead of MIDII-Scene vs MIDI · BlendSwap & ScenethesisCD-S: 0.0212 -> 0.0059Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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