ONeRF: Unsupervised 3D Object Segmentation from Multiple Views
This addresses the need for unsupervised 3D object segmentation in computer vision, enabling scene editing applications, and is incremental as it builds on existing NeRF methods.
The paper tackles the problem of automatically segmenting and reconstructing 3D object instances from multi-view RGB images without manual annotations, achieving results that handle complex shapes and topologies using separate Neural Radiance Fields.
We present ONeRF, a method that automatically segments and reconstructs object instances in 3D from multi-view RGB images without any additional manual annotations. The segmented 3D objects are represented using separate Neural Radiance Fields (NeRFs) which allow for various 3D scene editing and novel view rendering. At the core of our method is an unsupervised approach using the iterative Expectation-Maximization algorithm, which effectively aggregates 2D visual features and the corresponding 3D cues from multi-views for joint 3D object segmentation and reconstruction. Unlike existing approaches that can only handle simple objects, our method produces segmented full 3D NeRFs of individual objects with complex shapes, topologies and appearance. The segmented ONeRfs enable a range of 3D scene editing, such as object transformation, insertion and deletion.