Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry
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).
Code (0)
등록된 구현이 없습니다.
Tasks
3D ReconstructionSimilar Papers 제목 키워드 기반
An Efficient Quasi-Random Sampling for Copulas
This paper examines an efficient method for quasi-random sampling of copulas in Monte Carlo computations. Traditional methods, like conditional distribution methods (CDM), have limitations when dealing with high-dimensio…
ManagementQuasi-Monte Carlo sampling for machine-learning partial differential equations
Solving partial differential equations in high dimensions by deep neural network has brought significant attentions in recent years. In many scenarios, the loss function is defined as an integral over a high-dimensional …
BIG-bench Machine LearningNumerical IntegrationCombining Normalizing Flows and Quasi-Monte Carlo
Recent advances in machine learning have led to the development of new methods for enhancing Monte Carlo methods such as Markov chain Monte Carlo (MCMC) and importance sampling (IS). One such method is normalizing flows,…
Numerical IntegrationQuasi-Newton Quasi-Monte Carlo for variational Bayes
Many machine learning problems optimize an objective that must be measured with noise. The primary method is a first order stochastic gradient descent using one or more Monte Carlo (MC) samples at each step. There are se…
Second-order methodsDemystifying Orthogonal Monte Carlo and Beyond
Orthogonal Monte Carlo (OMC) is a very effective sampling algorithm imposing structural geometric conditions (orthogonality) on samples for variance reduction. Due to its simplicity and superior performance as compared t…