3D object detection has recently become popular due to many applications in robotics, augmented reality, autonomy, and image retrieval.
Ranked #1 on Monocular 3D Object Detection on Google Objectron
In this work, we introduce DeepSDF, a learned continuous Signed Distance Function (SDF) representation of a class of shapes that enables high quality shape representation, interpolation and completion from partial and noisy 3D input data.
With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity.
Extracting geometric features from 3D scans or point clouds is the first step in applications such as registration, reconstruction, and tracking.
Ranked #1 on 3D Feature Matching on 3DMatch Benchmark
We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called IM-NET, for shape generation, aimed at improving the visual quality of the generated shapes.
In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.
Ranked #3 on 3D Object Classification on ModelNet40
However, there is little effort on using mesh data in recent years, due to the complexity and irregularity of mesh data.
In this work we address the challenging problem of multiview 3D surface reconstruction.
The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built on a set of planes.
Generative models for 3D geometric data arise in many important applications in 3D computer vision and graphics.