Zero-Shot Multi-Object Scene Completion
Abstract
We present a 3D scene completion method that recovers the complete geometry of multiple unseen objects in complex scenes from a single RGB-D image. Despite notable advancements in single-object 3D shape completion, high-quality reconstructions in highly cluttered real-world multi-object scenes remains a challenge. To address this issue, we propose OctMAE, an architecture that leverages an Octree U-Net and a latent 3D MAE to achieve high-quality and near real-time multi-object scene completion through both local and global geometric reasoning. Because a naive 3D MAE can be computationally intractable and memory intensive even in the latent space, we introduce a novel occlusion masking strategy and adopt 3D rotary embeddings, which significantly improves the runtime and scene completion quality. To generalize to a wide range of objects in diverse scenes, we create a large-scale photorealistic dataset, featuring a diverse set of 12K 3D object models from the Objaverse dataset which are rendered in multi-object scenes with physics-based positioning. Our method outperforms the current state-of-the-art on both synthetic and real-world datasets and demonstrates a strong zero-shot capability.
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2024
- DOI:
- 10.48550/arXiv.2403.14628
- arXiv:
- arXiv:2403.14628
- Bibcode:
- 2024arXiv240314628I
- Keywords:
-
- Computer Science - Computer Vision and Pattern Recognition
- E-Print:
- Published at ECCV 2024, Webpage: https://sh8.io/#/oct_mae