About

Image: MeshNet

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Datasets

Latest papers with code

Deep Implicit Templates for 3D Shape Representation

30 Nov 2020ZhengZerong/DeepImplicitTemplates

Deep implicit functions (DIFs), as a kind of 3D shape representation, are becoming more and more popular in the 3D vision community due to their compactness and strong representation power.

3D SHAPE REPRESENTATION

57
30 Nov 2020

On the Effectiveness of Weight-Encoded Neural Implicit 3D Shapes

17 Sep 2020nathanrgodwin/overfit-shapes

Many prior works have focused on _latent-encoded_ neural implicits, where a latent vector encoding of a specific shape is also fed as input.

3D SHAPE REPRESENTATION

18
17 Sep 2020

Novel View Synthesis from Single Images via Point Cloud Transformation

17 Sep 2020lhoangan/pc4novis

In this paper the argument is made that for true novel view synthesis of objects, where the object can be synthesized from any viewpoint, an explicit 3D shape representation isdesired.

3D SHAPE REPRESENTATION NOVEL VIEW SYNTHESIS

6
17 Sep 2020

Discrete Point Flow Networks for Efficient Point Cloud Generation

ECCV 2020 Regenerator/dpf-nets

Generative models have proven effective at modeling 3D shapes and their statistical variations.

3D SHAPE REPRESENTATION POINT CLOUD GENERATION

25
20 Jul 2020

Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

NeurIPS 2020 lioryariv/idr

In this work we address the challenging problem of multiview 3D surface reconstruction.

3D RECONSTRUCTION 3D SHAPE REPRESENTATION

172
22 Mar 2020

Curriculum DeepSDF

ECCV 2020 haidongz-usc/Curriculum-DeepSDF

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.

3D SHAPE REPRESENTATION REPRESENTATION LEARNING

55
19 Mar 2020

BSP-Net: Generating Compact Meshes via Binary Space Partitioning

CVPR 2020 czq142857/BSP-NET-original

The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built on a set of planes.

3D RECONSTRUCTION 3D SHAPE REPRESENTATION

144
16 Nov 2019