paper-with-me

홈 › Papers

Modular Primitives for High-Performance Differentiable Rendering

2020-11-06 · Samuli Laine, Janne Hellsten, Tero Karras, Yeongho Seol, Jaakko Lehtinen, Timo Aila

We present a modular differentiable renderer design that yields performance superior to previous methods by leveraging existing, highly optimized hardware graphics pipelines. Our design supports all crucial operations in a modern graphics pipeline: rasterizing large numbers of triangles, attribute interpolation, filtered texture lookups, as well as user-programmable shading and geometry processing, all in high resolutions. Our modular primitives allow custom, high-performance graphics pipelines to be built directly within automatic differentiation frameworks such as PyTorch or TensorFlow. As a motivating application, we formulate facial performance capture as an inverse rendering problem and show that it can be solved efficiently using our tools. Our results indicate that this simple and straightforward approach achieves excellent geometric correspondence between rendered results and reference imagery.

📄 PDF Abstract BibTeX arXiv:2011.03277

Code (1)

NVlabs/nvdiffrast 공식 구현 tf

Tasks

AttributeInverse RenderingVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

LinPrim: Linear Primitives for Differentiable Volumetric Rendering

2025-01-27 · Nicolas von Lützow, Matthias Nießner

Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many recent works build on NeRF …

NeRFNovel View Synthesis

UTrice: Unifying Primitives in Differentiable Ray Tracing and Rasterization via Triangles for Particle-Based 3D Scenes

2025-12-04 · Changhe Liu, Ehsan Javanmardi, Naren Bao, Alex Orsholits 외 arxiv

Ray tracing 3D Gaussian particles enables realistic effects such as depth of field, refractions, and flexible camera modeling for novel-view synthesis. However, existing methods trace Gaussians through proxy geometry, wh…

2D Triangle Splatting for Direct Differentiable Mesh Training

2025-06-23 · Kaifeng Sheng, Zheng Zhou, Yingliang Peng, Qianwei Wang

Differentiable rendering with 3D Gaussian primitives has emerged as a powerful method for reconstructing high-fidelity 3D scenes from multi-view images. While it offers improvements over NeRF-based methods, this represen…

NeRF

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives

2023-07-11 · NeurIPS 2023 11 · Tom Monnier, Jake Austin, Angjoo Kanazawa, Alexei A. Efros 외

Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fideli…

Physical Simulations

BG-Triangle: Bézier Gaussian Triangle for 3D Vectorization and Rendering

2025-03-18 · Minye Wu, Haizhao Dai, Kaixin Yao, Tinne Tuytelaars 외

Differentiable rendering enables efficient optimization by allowing gradients to be computed through the rendering process, facilitating 3D reconstruction, inverse rendering and neural scene representation learning. To e…

3DGS3D ReconstructionInverse RenderingRepresentation Learning+1