Locally Orderless Images for Optimization in Differentiable Rendering
This addresses convergence issues in inverse rendering for computer vision and graphics, though it appears incremental as it builds on existing gradient-handling approaches.
The paper tackles the problem of sparse gradients in differentiable rendering by introducing a method using locally orderless images, which maps pixels to histograms to preserve local variations, and demonstrates recovery of optimal parameters in inverse rendering tasks.
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.