TBR: Transport-Based Rendering with Deposition Strokes for Inverse Graphics
Tianqi Liu, Yushan Han, Hang Liu
Abstract
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.
Create a lesson
Related papers
SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image
Yu-Rou Tuan, Hao-Tang Tsui, Nicolas Ugrinovic et al.
Grid-Free Monte Carlo for Time-Dependent Diffusion
Zihong Zhou, Rohan Sawhney, Eugene d'Eon et al.
Hologram Representation via Quadratic Phase Gaussian Splatting
Haolong Wang, Yicheng Zhan, Kaan Akşit et al.
Gaussian Light Transport
Patrick Attimont, Kartic Subr, Cyril Soler
Learning Realistic Athletic Sprinting Without Demonstrations
William Wang, Nicholas Bianco, Guy Tevet et al.
ReCHOIR: Contact-guided Human Object Interaction Retargeting to Diverse Characters
Chaelin Kim, Seokhyeon Hong, Kwan Yun et al.