Differentiable Convex Polyhedra Optimization from Multi-view Images
This paper presents a novel approach for the differentiable rendering of convex polyhedra, addressing the limitations of recent methods that rely on implicit field supervision. Our technique introduces a strategy that combines non-differentiable computation of hyperplane intersection through duality transform with differentiable optimization for vertex positioning with three-plane intersection, enabling gradient-based optimization without the need for 3D implicit fields. This allows for efficient shape representation across a range of applications, from shape parsing to compact mesh reconstruction. This work not only overcomes the challenges of previous approaches but also sets a new standard for representing shapes with convex polyhedra.
Code (1)
Similar Papers 제목 키워드 기반
Consistency Conditions for Differentiable Surrogate Losses
The statistical consistency of surrogate losses for discrete prediction tasks is often checked via the condition of calibration. However, directly verifying calibration can be arduous. Recent work shows that for polyhedr…
Stochastic subGradient Methods with Linear Convergence for Polyhedral Convex Optimization
In this paper, we show that simple {Stochastic} subGradient Decent methods with multiple Restarting, named {\bf RSGD}, can achieve a \textit{linear convergence rate} for a class of non-smooth and non-strongly convex opti…
BIG-bench Machine LearningOn the convex hull of convex quadratic optimization problems with indicators
We consider the convex quadratic optimization problem with indicator variables and arbitrary constraints on the indicators. We show that a convex hull description of the associated mixed-integer set in an extended space …
On the complexity of PAC learning in Hilbert spaces
We study the problem of binary classification from the point of view of learning convex polyhedra in Hilbert spaces, to which one can reduce any binary classification problem. The problem of learning convex polyhedra in …
Binary ClassificationClassificationPAC learningA Linearly Convergent Conditional Gradient Algorithm with Applications to Online and Stochastic Optimization
Linear optimization is many times algorithmically simpler than non-linear convex optimization. Linear optimization over matroid polytopes, matching polytopes and path polytopes are example of problems for which we have s…
Open-Ended Question AnsweringStochastic Optimization