Semi-parametric Object Synthesis

07/24/2019
by   Andrea Palazzi, et al.
2

We present a new semi-parametric approach to synthesize novel views of an object from a single monocular image. First, we exploit man-made object symmetry and piece-wise planarity to integrate rich a-priori visual information into the novel viewpoint synthesis process. An Image Completion Network (ICN) then leverages 2.5D sketches rendered from a 3D CAD as guidance to generate a realistic image. In contrast to concurrent works, we do not rely solely on synthetic data but leverage instead existing datasets for 3D object detection to operate in a real-world scenario. Differently from competitors, our semi-parametric framework allows the handling of a wide range of 3D transformations. Thorough experimental analysis against state-of-the-art baselines shows the efficacy of our method both from a quantitative and a perceptive point of view. Code and supplementary material are available at: https://github.com/ndrplz/semiparametric

READ FULL TEXT

page 3

page 5

page 6

page 8

research
10/19/2021

Self-Supervised Object Detection via Generative Image Synthesis

We present SSOD, the first end-to-end analysis-by synthesis framework wi...
research
03/28/2023

Novel View Synthesis of Humans using Differentiable Rendering

We present a new approach for synthesizing novel views of people in new ...
research
11/24/2021

Human Pose Manipulation and Novel View Synthesis using Differentiable Rendering

We present a new approach for synthesizing novel views of people in new ...
research
04/29/2018

Semi-parametric Image Synthesis

We present a semi-parametric approach to photographic image synthesis fr...
research
10/11/2021

UrbanNet: Leveraging Urban Maps for Long Range 3D Object Detection

Relying on monocular image data for precise 3D object detection remains ...
research
03/07/2017

SRN: Side-output Residual Network for Object Symmetry Detection in the Wild

In this paper, we establish a baseline for object symmetry detection in ...

Please sign up or login with your details

Forgot password? Click here to reset