Supervised Descent Method for Solving Nonlinear Least Squares Problems in Computer Vision

05/03/2014
by   Xuehan Xiong, et al.
0

Many computer vision problems (e.g., camera calibration, image alignment, structure from motion) are solved with nonlinear optimization methods. It is generally accepted that second order descent methods are the most robust, fast, and reliable approaches for nonlinear optimization of a general smooth function. However, in the context of computer vision, second order descent methods have two main drawbacks: (1) the function might not be analytically differentiable and numerical approximations are impractical, and (2) the Hessian may be large and not positive definite. To address these issues, this paper proposes generic descent maps, which are average "descent directions" and rescaling factors learned in a supervised fashion. Using generic descent maps, we derive a practical algorithm - Supervised Descent Method (SDM) - for minimizing Nonlinear Least Squares (NLS) problems. During training, SDM learns a sequence of decent maps that minimize the NLS. In testing, SDM minimizes the NLS objective using the learned descent maps without computing the Jacobian or the Hessian. We prove the conditions under which the SDM is guaranteed to converge. We illustrate the effectiveness and accuracy of SDM in three computer vision problems: rigid image alignment, non-rigid image alignment, and 3D pose estimation. In particular, we show how SDM achieves state-of-the-art performance in the problem of facial feature detection. The code has been made available at www.humansensing.cs.cmu.edu/intraface.

READ FULL TEXT

page 2

page 6

page 11

page 15

research
07/08/2014

Regression-Based Image Alignment for General Object Categories

Gradient-descent methods have exhibited fast and reliable performance fo...
research
09/05/2017

A Generic Approach for Escaping Saddle points

A central challenge to using first-order methods for optimizing nonconve...
research
08/03/2022

Neural Nets with a Newton Conjugate Gradient Method on Multiple GPUs

Training deep neural networks consumes increasing computational resource...
research
07/13/2017

Discriminative Optimization: Theory and Applications to Computer Vision Problems

Many computer vision problems are formulated as the optimization of a co...
research
06/25/2021

Hessian informed mirror descent

Inspired by the recent paper (L. Ying, Mirror descent algorithms for min...
research
10/21/2020

Progressive Batching for Efficient Non-linear Least Squares

Non-linear least squares solvers are used across a broad range of offlin...
research
09/09/2018

LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo

Sum-of-squares objective functions are very popular in computer vision a...

Please sign up or login with your details

Forgot password? Click here to reset