Obj-NeRF: Extract Object NeRFs from Multi-view Images
This addresses a specific bottleneck in NeRF-based 3D reconstruction for downstream tasks like editing and mesh extraction, but it is incremental as it builds on existing segmentation and NeRF methods.
The paper tackles the problem of extracting a specific object's radiance field from multi-view images, which is challenging due to occlusion and background complexity, by proposing Obj-NeRF, a pipeline that combines 2D segmentation with 3D reconstruction to recover 3D geometry using a single prompt, and demonstrates its practicality in applications like object removal and editing.
Neural Radiance Fields (NeRFs) have demonstrated remarkable effectiveness in novel view synthesis within 3D environments. However, extracting a radiance field of one specific object from multi-view images encounters substantial challenges due to occlusion and background complexity, thereby presenting difficulties in downstream applications such as NeRF editing and 3D mesh extraction. To solve this problem, in this paper, we propose Obj-NeRF, a comprehensive pipeline that recovers the 3D geometry of a specific object from multi-view images using a single prompt. This method combines the 2D segmentation capabilities of the Segment Anything Model (SAM) in conjunction with the 3D reconstruction ability of NeRF. Specifically, we first obtain multi-view segmentation for the indicated object using SAM with a single prompt. Then, we use the segmentation images to supervise NeRF construction, integrating several effective techniques. Additionally, we construct a large object-level NeRF dataset containing diverse objects, which can be useful in various downstream tasks. To demonstrate the practicality of our method, we also apply Obj-NeRF to various applications, including object removal, rotation, replacement, and recoloring.