3D Shape Representation
39 papers with code • 0 benchmarks • 4 datasets
Image: MeshNet
Benchmarks
These leaderboards are used to track progress in 3D Shape Representation
Objectron
Dynamic FAUST
KeypointNet
Foot3D
Latest papers
GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision
lkeab/gsnet
•
•
ECCV 2020
GSNet utilizes a unique four-way feature extraction and fusion scheme and directly regresses 6DoF poses and shapes in a single forward pass.
Discrete Point Flow Networks for Efficient Point Cloud Generation
Regenerator/dpf-nets
•
•
ECCV 2020
Generative models have proven effective at modeling 3D shapes and their statistical variations.
Learning Local Neighboring Structure for Robust 3D Shape Representation
Mesh is a powerful data structure for 3D shapes.
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance
lioryariv/idr
•
•
NeurIPS 2020
In this work we address the challenging problem of multiview 3D surface reconstruction.
Local Implicit Grid Representations for 3D Scenes
Then, we use the decoder as a component in a shape optimization that solves for a set of latent codes on a regular grid of overlapping crops such that an interpolation of the decoded local shapes matches a partial or noisy observation.
Curriculum DeepSDF
haidongz-usc/Curriculum-DeepSDF
•
•
ECCV 2020
When learning to sketch, beginners start with simple and flexible shapes, and then gradually strive for more complex and accurate ones in the subsequent training sessions.
Local Deep Implicit Functions for 3D Shape
google/ldif
•
•
CVPR 2020
The goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape categories, and inference from depth camera observations.
BSP-Net: Generating Compact Meshes via Binary Space Partitioning
czq142857/BSP-NET-original
•
•
CVPR 2020
The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built on a set of planes.
Fully Convolutional Geometric Features
chrischoy/FCGF
•
•
International Conference on Computer vision 2019
Extracting geometric features from 3D scans or point clouds is the first step in applications such as registration, reconstruction, and tracking.
Learning Embedding of 3D models with Quadric Loss
Sharp features such as edges and corners play an important role in the perception of 3D models.
