Canonical 3D Deformer Maps: Unifying parametric and non-parametric methods for dense weakly-supervised category reconstruction

08/28/2020
by   David Novotny, et al.
4

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. Our method builds in a novel way on concepts from parametric deformation models, non-parametric 3D reconstruction, and canonical embeddings, combining their individual advantages. In particular, it learns to associate each image pixel with a deformation model of the corresponding 3D object point which is canonical, i.e. intrinsic to the identity of the point and shared across objects of the category. The result is a method that, given only sparse 2D supervision at training time, can, at test time, reconstruct the 3D shape and texture of objects from single views, while establishing meaningful dense correspondences between object instances. It also achieves state-of-the-art results in dense 3D reconstruction on public in-the-wild datasets of faces, cars, and birds.

READ FULL TEXT

page 4

page 6

page 8

page 12

page 16

page 17

page 18

page 19

research
05/12/2022

Topologically-Aware Deformation Fields for Single-View 3D Reconstruction

We present a framework for learning 3D object shapes and dense cross-obj...
research
11/25/2020

DRACO: Weakly Supervised Dense Reconstruction And Canonicalization of Objects

We present DRACO, a method for Dense Reconstruction And Canonicalization...
research
05/17/2021

StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects

We present StrobeNet, a method for category-level 3D reconstruction of a...
research
06/04/2019

Photo-Geometric Autoencoding to Learn 3D Objects from Unlabelled Images

We show that generative models can be used to capture visual geometry co...
research
06/17/2021

Discovering Relationships between Object Categories via Universal Canonical Maps

We tackle the problem of learning the geometry of multiple categories of...
research
12/23/2021

BANMo: Building Animatable 3D Neural Models from Many Casual Videos

Prior work for articulated 3D shape reconstruction often relies on speci...
research
03/28/2023

ASIC: Aligning Sparse in-the-wild Image Collections

We present a method for joint alignment of sparse in-the-wild image coll...

Please sign up or login with your details

Forgot password? Click here to reset