Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization
Yusuke Takimoto, Hiroyuki Sato, Hikari Takehara, Keishiro Uragaki,, Takehiro Tawara, Xiao Liang, Kentaro Oku, Wataru Kishimoto, Bo Zheng

TL;DR
Dressi is a hardware-agnostic differentiable renderer that leverages Vulkan-based automatic differentiation, enabling efficient, high-quality, and flexible rendering and inverse rendering applications across different hardware platforms.
Contribution
The paper introduces Dressi, a fully Vulkan-based, hardware-agnostic differentiable renderer with novel techniques like stage packing and HardSoftRas for inverse rendering.
Findings
Achieves hardware independence and acceleration using graphics hardware.
Provides high-quality, robust optimization with fast rendering speeds.
Demonstrates photorealistic rendering and effective inverse rendering applications.
Abstract
Differentiable rendering (DR) enables various computer graphics and computer vision applications through gradient-based optimization with derivatives of the rendering equation. Most rasterization-based approaches are built on general-purpose automatic differentiation (AD) libraries and DR-specific modules handcrafted using CUDA. Such a system design mixes DR algorithm implementation and algorithm building blocks, resulting in hardware dependency and limited performance. In this paper, we present a practical hardware-agnostic differentiable renderer called Dressi, which is based on a new full AD design. The DR algorithms of Dressi are fully written in our Vulkan-based AD for DR, Dressi-AD, which supports all primitive operations for DR. Dressi-AD and our inverse UV technique inside it bring hardware independence and acceleration by graphics hardware. Stage packing, our runtime…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Vision and Imaging · Computer Graphics and Visualization Techniques · Advanced Image Fusion Techniques
