NeRFDeformer: NeRF Transformation from a Single View via 3D Scene Flows
We present a method for automatically modifying a NeRF representation based on a single observation of a non-rigid transformed version of the original scene. Our method defines the transformation as a 3D flow, specifically as a weighted linear blending of rigid transformations of 3D anchor points that are defined on the surface of the scene. In order to identify anchor points, we introduce a novel correspondence algorithm that first matches RGB-based pairs, then leverages multi-view information and 3D reprojection to robustly filter false positives in two steps. We also introduce a new dataset for exploring the problem of modifying a NeRF scene through a single observation. Our dataset ( https://github.com/nerfdeformer/nerfdeformer ) contains 113 synthetic scenes leveraging 47 3D assets. We show that our proposed method outperforms NeRF editing methods as well as diffusion-based methods, and we also explore different methods for filtering correspondences.
Code (1)
Tasks
NeRFSimilar Papers 제목 키워드 기반
To View Transform or Not to View Transform: NeRF-based Pre-training Perspective
Neural radiance fields (NeRFs) have emerged as a prominent pre-training paradigm for vision-centric autonomous driving, which enhances 3D geometry and appearance understanding in a fully self-supervised manner. To apply …
Representation LearningScene UnderstandingAutonomous DrivingSymmNeRF: Learning to Explore Symmetry Prior for Single-View View Synthesis
We study the problem of novel view synthesis of objects from a single image. Existing methods have demonstrated the potential in single-view view synthesis. However, they still fail to recover the fine appearance details…
NeRFNovel View SynthesisSinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image
Despite the rapid development of Neural Radiance Field (NeRF), the necessity of dense covers largely prohibits its wider applications. While several recent works have attempted to address this issue, they either operate …
NeRFNovel View Synthesis4D-Editor: Interactive Object-level Editing in Dynamic Neural Radiance Fields via Semantic Distillation
This paper targets interactive object-level editing (e.g., deletion, recoloring, transformation, composition) in dynamic scenes. Recently, some methods aiming for flexible editing static scenes represented by neural radi…
NeRFSemantic SegmentationONeRF: Unsupervised 3D Object Segmentation from Multiple Views
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…
3D scene EditingObjectSemantic Segmentation