Shape and Viewpoint without Keypoints

07/21/2020
by   Shubham Goel, et al.
2

We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera viewpoints or keypoint supervision. We approach this highly under-constrained problem in a "analysis by synthesis" framework where the goal is to predict the likely shape, texture and camera viewpoint that could produce the image with various learned category-specific priors. Our particular contribution in this paper is a representation of the distribution over cameras, which we call "camera-multiplex". Instead of picking a point estimate, we maintain a set of camera hypotheses that are optimized during training to best explain the image given the current shape and texture. We call our approach Unsupervised Category-Specific Mesh Reconstruction (U-CMR), and present qualitative and quantitative results on CUB, Pascal 3D and new web-scraped datasets. We obtain state-of-the-art camera prediction results and show that we can learn to predict diverse shapes and textures across objects using an image collection without any keypoint annotations or 3D ground truth. Project page: https://shubham-goel.github.io/ucmr

READ FULL TEXT

page 1

page 12

page 13

page 21

page 22

page 23

page 24

page 25

research
03/20/2018

Learning Category-Specific Mesh Reconstruction from Image Collections

We present a learning framework for recovering the 3D shape, camera, and...
research
09/03/2021

CodeNeRF: Disentangled Neural Radiance Fields for Object Categories

CodeNeRF is an implicit 3D neural representation that learns the variati...
research
03/22/2015

Lifting Object Detection Datasets into 3D

While data has certainly taken the center stage in computer vision in re...
research
06/10/2021

To The Point: Correspondence-driven monocular 3D category reconstruction

We present To The Point (TTP), a method for reconstructing 3D objects fr...
research
12/01/2022

ViewNeRF: Unsupervised Viewpoint Estimation Using Category-Level Neural Radiance Fields

We introduce ViewNeRF, a Neural Radiance Field-based viewpoint estimatio...
research
06/15/2023

NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations

Recent advances in neural reconstruction enable high-quality 3D object r...
research
04/27/2022

3D Magic Mirror: Clothing Reconstruction from a Single Image via a Causal Perspective

This research aims to study a self-supervised 3D clothing reconstruction...

Please sign up or login with your details

Forgot password? Click here to reset