mlsanityData to 14 Oct 2026

TBR: Transport-Based Rendering with Deposition Strokes for Inverse Graphics

arXiv 2609.08722 ↗First posted 8 Sep 2026cs.GR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a stroke design in which strokes are transport-coupled: each stroke deposits material of its own area and moves every earlier mark without changing its area, so later strokes deform earlier ones. We then solve the inverse problem under this design: given a target image, we optimise an ordered program of such strokes whose replay approximates it, with digital marbling as the motivating medium. The stroke is a capsule that continuously joins circular drops to drawn deposits; its transport is exactly area-preserving, with a closed-form inverse outside the deposit, and a variant with the same inverse differs from line-source potential flow by 8% of the mean displacement. A replay adjoint regenerates intermediate states instead of storing them and uses 8.7x less memory than checkpointed automatic differentiation; a fused implementation fits a 2000-stroke program at 1024x1024 in about four minutes on one GPU. On five marbled sheets the recovered programs are level with a published stroke-based fitter as rasters, replay across a fourfold resolution range, and support edits in program order and palette space that stay valid under transport.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 35 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

15 of 35 references.

References · 15

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  3. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  4. 2015Gradient-based Hyperparameter Optimization through Reversible Learningcited by 360
  5. 2019DiffTaichi: Differentiable Programming for Physical Simulationcited by 258
  6. 2017The Reversible Residual Network: Backpropagation Without Storing Activationscited by 217
  7. 2022Towards Layer-wise Image Vectorizationcited by 79
  8. 2017Learning to Infer Graphics Programs from Hand-Drawn Imagescited by 74
  9. 2019Learning to Paint With Model-based Deep Reinforcement Learningcited by 71
  10. 2021Paint Transformer: Feed Forward Neural Painting with Stroke Predictioncited by 62
  11. 2020Stylized Neural Paintingcited by 50
  12. 2022FRIDA: A Collaborative Robot Painter with a Differentiable, Real2Sim2Real Planning Environmentcited by 18
3 more
  1. 2025An Adjoint Method for Differentiable Fluid Simulation on Flow Mapscited by 2
  2. 2025Birth of a Painting: Differentiable Brushstroke Reconstructioncited by 1
  3. 2026Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulationcited by 1

Built on by

Not cited yet.