Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry

07/27/2020
by   Yifan Xu, et al.
0

Deep implicit field regression methods are effective for 3D reconstruction from single-view images. However, the impact of different sampling patterns on the reconstruction quality is not well-understood. In this work, we first study the effect of point set discrepancy on the network training. Based on Farthest Point Sampling algorithm, we propose a sampling scheme that theoretically encourages better generalization performance, and results in fast convergence for SGD-based optimization algorithms. Secondly, based on the reflective symmetry of an object, we propose a feature fusion method that alleviates issues due to self-occlusions which makes it difficult to utilize local image features. Our proposed system Ladybird is able to create high quality 3D object reconstructions from a single input image. We evaluate Ladybird on a large scale 3D dataset (ShapeNet) demonstrating highly competitive results in terms of Chamfer distance, Earth Mover's distance and Intersection Over Union (IoU).

READ FULL TEXT

page 5

page 15

research
05/26/2019

DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction

Reconstructing 3D shapes from single-view images has been a long-standin...
research
04/01/2023

SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction

We address the problem of clothed human reconstruction from a single ima...
research
08/20/2019

Probabilistic Reconstruction Networks for 3D Shape Inference from a Single Image

We study end-to-end learning strategies for 3D shape inference from imag...
research
09/06/2021

Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images

Recovering the 3D structure of an object from a single image is a challe...
research
02/02/2022

Extension: Adaptive Sampling with Implicit Radiance Field

This manuscript discusses the extension of adaptive light field sampling...
research
06/14/2022

Reconstructing vehicles from orthographic drawings using deep neural networks

This paper explores the current state-of-the-art of object reconstructio...
research
01/29/2021

Towards Generalising Neural Implicit Representations

Neural implicit representations have shown substantial improvements in e...

Please sign up or login with your details

Forgot password? Click here to reset