arXiv (Cornell University) · 2021 · 29 citations · 40 references
ComputingComputer ScienceComputer VisionMachine LearningMachine Vision3D Imaging3D ReconstructionDeep LearningScene ReconstructionScene UnderstandingVolume Segmentation3D Image Segmentation3D Scene UnderstandingNeural Radiance Fields
We present ObSuRF, a method which turns a single image of a scene into a 3D model represented as a set of Neural Radiance Fields (NeRFs), with each NeRF corresponding to a different object. A single forward pass of an encoder network outputs a set of latent vectors describing the objects in the scene. These vectors are used independently to condition a NeRF decoder, defining the geometry and appearance of each object. We make learning more computationally efficient by deriving a novel loss, which allows training NeRFs on RGB-D inputs without explicit ray marching. After confirming that the model performs equal or better than state of the art on three 2D image segmentation benchmarks, we apply it to two multi-object 3D datasets: A multiview version of CLEVR, and a novel dataset in which scenes are populated by ShapeNet models. We find that after training ObSuRF on RGB-D views of training scenes, it is capable of not only recovering the 3D geometry of a scene depicted in a single input image, but also to segment it into objects, despite receiving no supervision in that regard.
40
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Raffaelli Charles, Hao Su, Kaichun Mo et al. · 2017 · 9.8K citations
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Charles R. Qi, Hao Su, Kaichun Mo et al. · arXiv (Cornell University) · 2016 · 2.9K citations · Full text