We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction.
Traditional approaches for learning 3D object categories have been predominantly trained and evaluated on synthetic datasets due to the unavailability of real 3D-annotated category-centric data.
The method learns, in an end-to-end fashion, a soft partition of a given category-specific 3D template mesh into rigid parts together with a monocular reconstruction network that predicts the part motions such that they reproject correctly onto 2D DensePose-like surface annotations of the object.
Implicit neural representation is a recent approach to learn shape collections as zero level-sets of neural networks, where each shape is represented by a latent code.
We present NeuroMorph, a new neural network architecture that takes as input two 3D shapes and produces in one go, i. e. in a single feed forward pass, a smooth interpolation and point-to-point correspondences between them.
Recent work has shown that it is possible to learn a unified dense pose predictor for several categories of related objects.
Our goal is to learn a deep network that, given a small number of images of an object of a given category, reconstructs it in 3D.
In this work, we focus on the task of learning and representing dense correspondences in deformable object categories.
Using a set of high-quality sparse keypoint matches, we optimize over the per-frame linear combinations of depth planes and camera poses to form a geometrically consistent cloud of keypoints.
We consider the problem of obtaining dense 3D reconstructions of humans from single and partially occluded views.
We propose the Canonical 3D Deformer Map, a new representation of the 3D shape of common object categories that can be learned from a collection of 2D images of independent objects.
We address these challenges by introducing PyTorch3D, a library of modular, efficient, and differentiable operators for 3D deep learning.
Given a set of a reference RGBD views of an indoor environment, and a new viewpoint, our goal is to predict the view from that location.
We show that these models, by understanding uncertainty better, can solve the original DensePose task more accurately, thus setting the new state-of-the-art accuracy in this benchmark.
We propose C3DPO, a method for extracting 3D models of deformable objects from 2D keypoint annotations in unconstrained images.
Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks.
Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG.
While recent research in image understanding has often focused on recognizing more types of objects, understanding more about the objects is just as important.