Jan 07, 2026
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
Jul 13, 2026
The paper''s main technical idea, Differentiable Parameter Propagation (DPP), pushes pixel-level constraint violations back through a lightweight differentiable rasterizer during fine-tuning.
Jan 23, 2026
Our core technical contribution is Differentiable Parameter Propagation (DPP), a training method that embeds hard design constraints into vision-language model fine-tuning by
Jun 14, 2026
Inspired by tiny renderer, this tiny course aims to implement, explain, and explore state-of-the-art approaches to differentiable triangle rasterization. Differentiable rasterization is a type of inverse
Mar 15, 2026
Concretely, we introduce a meta-learning strategy to learn the optimal edge and occlusion softness for a differentiable rasterizer in the form of an Multi-layer Perceptron (MLP).
Sep 27, 2025
Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation. By inverting such renderer, one can think of a learning approach to infer
Mar 11, 2026
Nvdiffrast offers four differentiable rendering primitives: rasterization, interpolation, texturing, and antialiasing. The operation of the primitives is described here in a
Jan 22, 2026
We introduce a differentiable rasterizer that bridges the vector graphics and raster image domains, enabling powerful raster-based loss functions, opti-mization procedures, and machine learning
Jan 28, 2026
We call our framework Soft Rasterizer (SoftRas) as it “softens” the discrete rasterization to enable differentiability. Thanks to the consistent forward and backward propaga-tions, SoftRas is able to
May 11, 2026
Differentiable rasterization is a family of techniques that enable the propagation of gradients through the traditionally discrete process of projection and sampling that forms the basis of
Nov 26, 2025
We introduce a differentiable rasterizer for vector graphics that bridges the raster and vector domains through backpropagation. Differentiable rasterization enables many novel vector graphics
Nov 20, 2025
Overview of 3DGS . 3DGS reconstructs a scene with 3D Gaussian from multi-view images, employs a differentiable rasterizer for rendering, and optimizes the scene representation through density
Aug 21, 2025
However, standard rendering pipelines involve a fundamental discretization step called rasterization, which prevents the rendering process to be differentiable, hence suitable for learning.
Apr 18, 2026
To address this issue, a novel differentiable hardware rasterizer tailored for 3DGS has been introduced. This innovative solution effectively overcomes the limitations in memory and performance associated
Aug 09, 2025
By inverting such renderer, one can think of a learning approach to infer 3D information from 2D images. However, standard graphics renderers involve a fundamental discretization step
Jun 27, 2026
Soft Rasterizer (SoftRas) is a truly differentiable renderer framework with a novel formulation that views rendering as a differentiable aggregating process that fuses probabilistic contributions of all mesh
Mar 23, 2026
And that''s it! We have a differentiable rasterizer. A bit of work, but only really one custom derivative and the rest we got from the framework for free. Example 1:
Sep 22, 2025
The pipeline generally runs in four stages: capture (photos or video from many angles), structure-from-motion to recover camera positions and a sparse point cloud, Gaussian initialization
Oct 07, 2025
Differentiable rasterization changes the standard formulation of primitive rasterization -- by enabling gradient flow from a pixel to its underlying triangles -- using distribution functions in
We Look Forward to Working with You