paper-with-me

홈 › Papers

Learning to Rasterize Differentiably

2022-11-23 · Chenghao Wu, Hamila Mailee, Zahra Montazeri, Tobias Ritschel

Differentiable rasterization changes the standard formulation of primitive rasterization -- by enabling gradient flow from a pixel to its underlying triangles -- using distribution functions in different stages of rendering, creating a "soft" version of the original rasterizer. However, choosing the optimal softening function that ensures the best performance and convergence to a desired goal requires trial and error. Previous work has analyzed and compared several combinations of softening. In this work, we take it a step further and, instead of making a combinatorial choice of softening operations, parameterize the continuous space of common softening operations. We study meta-learning tunable softness functions over a set of inverse rendering tasks (2D and 3D shape, pose and occlusion) so it generalizes to new and unseen differentiable rendering tasks with optimal softness.

📄 PDF Abstract BibTeX arXiv:2211.13333

Code (1)

theo-wu/metaras 공식 구현 pytorch

Tasks

Inverse RenderingMeta-Learning

Similar Papers 제목 키워드 기반

Rasterized Edge Gradients: Handling Discontinuities Differentiably

2024-05-03 · Stanislav Pidhorskyi, Tomas Simon, Gabriel Schwartz, He Wen 외

Computing the gradients of a rendering process is paramount for diverse applications in computer vision and graphics. However, accurate computation of these gradients is challenging due to discontinuities and rendering a…

Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks

2020-07-22 · ICCV 2021 10 · Kirill Mazur, Victor Lempitsky

We present a new versatile building block for deep point cloud processing architectures that is equally suited for diverse tasks. This building block combines the ideas of spatial transformers and multi-view convolutiona…

Point Cloud ClassificationPoint cloud reconstructionPoint Cloud SegmentationSemantic Segmentation

Coordinate descent heuristics for the irregular strip packing problem of rasterized shapes

2021-04-09 · Shunji Umetani, Shohei Murakami

We consider the irregular strip packing problem of rasterized shapes, where a given set of pieces of irregular shapes represented in pixels should be placed into a rectangular container without overlap. The rasterized sh…

Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction

2019-01-17 · Shichen Liu, Weikai Chen, Tianye Li, Hao Li

Rendering is the process of generating 2D images from 3D assets, simulated in a virtual environment, typically with a graphics pipeline. By inverting such renderer, one can think of a learning approach to predict a 3D sh…

Rasterized Steered Mixture of Experts for Efficient 2D Image Regression

2025-10-07 · Yi-Hsin Li, Mårten Sjöström, Sebastian Knorr, Thomas Sikora arxiv

The Steered Mixture of Experts regression framework has demonstrated strong performance in image reconstruction, compression, denoising, and super-resolution. However, its high computational cost limits practical applica…

Computational EfficiencyImage ReconstructionImage Denoising