mlsanityData to 7 Oct 2026

Learning to Rasterize Differentiably

arXiv 2211.13333 ↗First posted 23 Nov 2022cs.GR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 23 references that are in the map. First posted on arXiv 23 Nov 2022.

Builds on

12 of 23 references.

References · 12

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  3. 2017Neural 3D Mesh Renderercited by 437
  4. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  5. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  6. 2020Differentiable Rendering: A Surveycited by 123
  7. 2021DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderercited by 52
  8. 2016A Versatile Scene Model with Differentiable Visibility Applied to Generative Pose Estimationcited by 42
  9. 2021Learning with Algorithmic Supervision via Continuous Relaxationscited by 21
  10. 2019Pix2Vex: Image-to-Geometry Reconstruction using a Smooth Differentiable Renderercited by 18
  11. 2022GenDR: A Generalized Differentiable Renderercited by 12
  12. 2020End-to-End Differentiable 6DoF Object Pose Estimation with Local and Global Constraintscited by 1

Built on by

Not cited yet.