InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes
Journal:
arXiv
Published Date:
Jul 11, 2025
Abstract
Humans can naturally identify and mentally complete occluded objects in
cluttered environments. However, imparting similar cognitive ability to
robotics remains challenging even with advanced reconstruction techniques,
which models scenes as undifferentiated wholes and fails to recognize complete
object from partial observations. In this paper, we propose InstaScene, a new
paradigm towards holistic 3D perception of complex scenes with a primary goal:
decomposing arbitrary instances while ensuring complete reconstruction. To
achieve precise decomposition, we develop a novel spatial contrastive learning
by tracing rasterization of each instance across views, significantly enhancing
semantic supervision in cluttered scenes. To overcome incompleteness from
limited observations, we introduce in-situ generation that harnesses valuable
observations and geometric cues, effectively guiding 3D generative models to
reconstruct complete instances that seamlessly align with the real world.
Experiments on scene decomposition and object completion across complex
real-world and synthetic scenes demonstrate that our method achieves superior
decomposition accuracy while producing geometrically faithful and visually
intact objects.
