Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction
The goal of this paper is to compare surface-based and volumetric 3D object shape representations, as well as viewer-centered and object-centered reference frames for single-view 3D shape prediction. We propose a new algorithm for predicting depth maps from multiple viewpoints, with a single depth or RGB image as input. By modifying the network and the way models are evaluated, we can directly compare the merits of voxels vs. surfaces and viewer-centered vs. object-centered for familiar vs. unfamiliar objects, as predicted from RGB or depth images. Among our findings, we show that surface-based methods outperform voxel representations for objects from novel classes and produce higher resolution outputs. We also find that using viewer-centered coordinates is advantageous for novel objects, while object-centered representations are better for more familiar objects. Interestingly, the coordinate frame significantly affects the shape representation learned, with object-centered placing more importance on implicitly recognizing the object category and viewer-centered producing shape representations with less dependence on category recognition.
Code (0)
등록된 구현이 없습니다.
Tasks
ObjectSimilar Papers 제목 키워드 기반
Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. Previous work on learning shape reconstruction from multiple views uses…
Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields
Most existing CNN-based methods for single-view 3D object reconstruction represent a 3D object as either a 3D voxel occupancy grid or multiple depth-mask image pairs. However, these representations are inefficient since …
3D Object ReconstructionObjectObject ReconstructionSPARF: Large-Scale Learning of 3D Sparse Radiance Fields from Few Input Images
Recent advances in Neural Radiance Fields (NeRFs) treat the problem of novel view synthesis as Sparse Radiance Field (SRF) optimization using sparse voxels for efficient and fast rendering (plenoxels,InstantNGP). In orde…
Novel View SynthesisSynthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes With Deep Generative Networks
We study the problem of learning generative models of 3D shapes. Voxels or 3D parts have been widely used as the underlying representations to build complex 3D shapes; however, voxel-based representations suffer from hig…
Representation-Agnostic Shape Fields
3D shape analysis has been widely explored in the era of deep learning. Numerous models have been developed for various 3D data representation formats, e.g., MeshCNN for meshes, PointNet for point clouds and VoxNet for v…
Deep Learning