Canonical 3D Deformer Maps: Unifying parametric and non-parametric
methods for dense weakly-supervised category reconstruction
- URL: http://arxiv.org/abs/2008.12709v2
- Date: Sun, 6 Dec 2020 11:59:06 GMT
- Title: Canonical 3D Deformer Maps: Unifying parametric and non-parametric
methods for dense weakly-supervised category reconstruction
- Authors: David Novotny, Roman Shapovalov, Andrea Vedaldi
- Abstract summary: We propose 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.
It achieves state-of-the-art results in dense 3D reconstruction on public in-the-wild datasets of faces, cars, and birds.
- Score: 79.98689027127855
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction [67.13370009386635]
We introduce the Dual Point Maps (DualPM), where a pair of point maps is extracted from the same image, one associating pixels to their 3D locations on the object, and the other to a canonical version of the object at rest pose.
We show that 3D reconstruction and 3D pose estimation reduce to the prediction of the DualPMs.
arXiv Detail & Related papers (2024-12-05T18:59:48Z) - 3D Surface Reconstruction in the Wild by Deforming Shape Priors from
Synthetic Data [24.97027425606138]
Reconstructing the underlying 3D surface of an object from a single image is a challenging problem.
We present a new method for joint category-specific 3D reconstruction and object pose estimation from a single image.
Our approach achieves state-of-the-art reconstruction performance across several real-world datasets.
arXiv Detail & Related papers (2023-02-24T20:37:27Z) - Topologically-Aware Deformation Fields for Single-View 3D Reconstruction [30.738926104317514]
We present a new framework for learning 3D object shapes and dense cross-object 3D correspondences from just an unaligned category-specific image collection.
The 3D shapes are generated implicitly as deformations to a category-specific signed distance field.
Our approach, dubbed TARS, achieves state-of-the-art reconstruction fidelity on several datasets.
arXiv Detail & Related papers (2022-05-12T17:59:59Z) - ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes [55.689763519293464]
ConDor is a self-supervised method that learns to canonicalize the 3D orientation and position for full and partial 3D point clouds.
During inference, our method takes an unseen full or partial 3D point cloud at an arbitrary pose and outputs an equivariant canonical pose.
arXiv Detail & Related papers (2022-01-19T18:57:21Z) - End-to-End Learning of Multi-category 3D Pose and Shape Estimation [128.881857704338]
We propose an end-to-end method that simultaneously detects 2D keypoints from an image and lifts them to 3D.
The proposed method learns both 2D detection and 3D lifting only from 2D keypoints annotations.
In addition to being end-to-end in image to 3D learning, our method also handles objects from multiple categories using a single neural network.
arXiv Detail & Related papers (2021-12-19T17:10:40Z) - DensePose 3D: Lifting Canonical Surface Maps of Articulated Objects to
the Third Dimension [71.71234436165255]
We contribute DensePose 3D, a method that can learn such reconstructions in a weakly supervised fashion from 2D image annotations only.
Because it does not require 3D scans, DensePose 3D can be used for learning a wide range of articulated categories such as different animal species.
We show significant improvements compared to state-of-the-art non-rigid structure-from-motion baselines on both synthetic and real data on categories of humans and animals.
arXiv Detail & Related papers (2021-08-31T18:33:55Z) - Learning Canonical 3D Object Representation for Fine-Grained Recognition [77.33501114409036]
We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image.
We represent an object as a composition of 3D shape and its appearance, while eliminating the effect of camera viewpoint.
By incorporating 3D shape and appearance jointly in a deep representation, our method learns the discriminative representation of the object.
arXiv Detail & Related papers (2021-08-10T12:19:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.