SAMV-DUSt3R: Instance-Centric 3D Scene Decoupling from Sparse Multi-Views

2026-09-10

AI Summary

为了解决3D场景中物体分离问题，提出SAMV-DUSt3R模型，通过注入2D掩码并使用轻量级Spatial RankGNN选择最佳视角，提高了重建精度和对象级解耦能力。

Abstract

With the rising demand to decouple objects from 3D scenes, we propose SAMV-DUSt3R, an end-to-end model that injects SAM2 2D masks into MV-DUSt3R reconstruction. A Cross Flow Mask Block uses these masks to steer the network toward the target instance, jointly improving shape accuracy and achieving object-level disentanglement without multi-stage pipelines. To ensure reconstruction stability, a lightweight Spatial RankGNN selects the optimal reference view with a selection accuracy of 73.5\%. Extensive experiments demonstrate that our method boosts average reconstruction precision by 11\% across various metrics compared to state-of-the-art baselines. These results reveal a strong instance-disentanglement capability and clear benefits for driving, robotics, AR/VR, and heritage digitisation.

Problem

• 3D Scene Decoupling
• Sparse Multi-Views
• Instance-Centric
• Shape Accuracy
• Object-Level Disentanglement

Innovation

• end-to-end model
• Cross Flow Mask Block
• Spatial RankGNN
• instance-centric 3D scene decoupling