SAOR: Single-View Articulated Object Reconstruction

03/23/2023
by   Mehmet Aygün, et al.
0

We introduce SAOR, a novel approach for estimating the 3D shape, texture, and viewpoint of an articulated object from a single image captured in the wild. Unlike prior approaches that rely on pre-defined category-specific 3D templates or tailored 3D skeletons, SAOR learns to articulate shapes from single-view image collections with a skeleton-free part-based model without requiring any 3D object shape priors. To prevent ill-posed solutions, we propose a cross-instance consistency loss that exploits disentangled object shape deformation and articulation. This is helped by a new silhouette-based sampling mechanism to enhance viewpoint diversity during training. Our method only requires estimated object silhouettes and relative depth maps from off-the-shelf pre-trained networks during training. At inference time, given a single-view image, it efficiently outputs an explicit mesh representation. We obtain improved qualitative and quantitative results on challenging quadruped animals compared to relevant existing work.

READ FULL TEXT

page 1

page 6

page 7

page 8

page 12

page 13

page 14

page 16

research
11/22/2022

MagicPony: Learning Articulated 3D Animals in the Wild

We consider the problem of learning a function that can estimate the 3D ...
research
04/21/2022

Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

Approaches for single-view reconstruction typically rely on viewpoint an...
research
04/14/2013

Single View Depth Estimation from Examples

We describe a non-parametric, "example-based" method for estimating the ...
research
03/08/2020

Meta3D: Single-View 3D Object Reconstruction from Shape Priors in Memory

3D shape reconstruction from a single-view RGB image is an ill-posed pro...
research
09/06/2018

3D Surface Reconstruction by Pointillism

The objective of this work is to infer the 3D shape of an object from a ...
research
05/14/2021

Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches

We investigate the problem of generating 3D meshes from single free-hand...
research
04/20/2023

Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion

We present Farm3D, a method to learn category-specific 3D reconstructors...

Please sign up or login with your details

Forgot password? Click here to reset