Locally Orderless Images for Optimization in Differentiable Rendering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mehta, Ishit, Chandraker, Manmohan, Ramamoorthi, Ravi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910897517101056
author Mehta, Ishit
Chandraker, Manmohan
Ramamoorthi, Ravi
author_facet Mehta, Ishit
Chandraker, Manmohan
Ramamoorthi, Ravi
contents Problems in differentiable rendering often involve optimizing scene parameters that cause motion in image space. The gradients for such parameters tend to be sparse, leading to poor convergence. While existing methods address this sparsity through proxy gradients such as topological derivatives or lagrangian derivatives, they make simplifying assumptions about rendering. Multi-resolution image pyramids offer an alternative approach but prove unreliable in practice. We introduce a method that uses locally orderless images, where each pixel maps to a histogram of intensities that preserves local variations in appearance. Using an inverse rendering objective that minimizes histogram distance, our method extends support for sparsely defined image gradients and recovers optimal parameters. We validate our method on various inverse problems using both synthetic and real data.
format Preprint
id arxiv_https___arxiv_org_abs_2503_21931
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Locally Orderless Images for Optimization in Differentiable Rendering
Mehta, Ishit
Chandraker, Manmohan
Ramamoorthi, Ravi
Graphics
Computer Vision and Pattern Recognition
Problems in differentiable rendering often involve optimizing scene parameters that cause motion in image space. The gradients for such parameters tend to be sparse, leading to poor convergence. While existing methods address this sparsity through proxy gradients such as topological derivatives or lagrangian derivatives, they make simplifying assumptions about rendering. Multi-resolution image pyramids offer an alternative approach but prove unreliable in practice. We introduce a method that uses locally orderless images, where each pixel maps to a histogram of intensities that preserves local variations in appearance. Using an inverse rendering objective that minimizes histogram distance, our method extends support for sparsely defined image gradients and recovers optimal parameters. We validate our method on various inverse problems using both synthetic and real data.
title Locally Orderless Images for Optimization in Differentiable Rendering
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.21931