AI Paper Atlas

Research map / Detection and segmentation / CNN features

AGE: Agentic Gaussian Editing in 3D Scenarios

Hao Qin, Tesi Lin, Mingwei Wei, Yukai Sun, Mengxu Lu, Ming Kong, Qiang Zhu

ECCV 2026 · Detection and segmentation › CNN features · approach: Domain-specific segmentation and detection · 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
replace one-shot pipeline editing with multi-agent planner/executor/reflector/backtracker with structured memoryAGE vs DGE · 57-scenario 3D editing benchmarkCsim: 0.133 -> 0.192Improved
multi-agent closed-loop editing vs DGE on multi-view consistencyAGE vs DGE · 57-scenario 3D editing benchmarkCcon: 0.892 -> 0.907Improved
multi-agent closed-loop editing vs DGEAGE vs DGE · 57-scenario 3D editing benchmarkIAA: 5.79 -> 6.65Improved
multi-agent closed-loop editing vs DGE, LLM judge structural consistencyAGE vs DGE · LLM-judge evaluationstructural consistency: 7.39 -> 8.90Improved
multi-agent closed-loop editing vs GaussianEditor, LLM judge completion degreeAGE vs GaussianEditor · LLM-judge evaluationcompletion degree: 5.70 -> 7.17Improved

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