awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
daniilidis-group avatar

daniilidis-group/neural_renderer

0
View on GitHub↗
1,165 stars·255 forks·Python·21 views

Neural Renderer

Neural renderer is a differentiable rendering library for PyTorch that projects three-dimensional meshes into two-dimensional images while maintaining continuous mathematical gradients for backpropagation. The framework enables gradient-based inverse rendering, allowing optimization of input parameters such as camera pose, vertex positions, and texture maps by propagating pixel-level reconstruction errors backward to the source geometry.

The architecture incorporates approximate rasterisation gradients that substitute discontinuous edge derivatives with heuristic approximations to facilitate gradient flow across geometric silhouette boundaries during rendering. Additional capabilities include perspective-correct rasterisation texture interpolation, camera parameter estimation, and multi-dimensional tensor integration that leverages deep learning framework features.

Features

  • Differentiable Rendering - Provides a differentiable rendering library that computes image derivatives relative to camera pose and geometry.
  • Image-Based 3D Reconstructions - Optimizes three-dimensional geometry and appearance parameters directly from two-dimensional supervision signals.
  • PyTorch Tensor Operations - Operates directly on multi-dimensional tensors to leverage hardware acceleration and automatic differentiation.
  • Inverse Rendering Frameworks - Optimizes input parameters like camera pose and vertex positions by propagating pixel-level reconstruction errors backward.
  • Differentiable Renderers - Projects three-dimensional meshes into two-dimensional images while maintaining gradients for deep learning optimization.
  • Differentiable Shape Optimization - Refines 3D geometry and appearance parameters directly from 2D supervision signals.
  • Camera Pose Estimators - Calculates camera orientations and positions from imagery to facilitate 3D reconstruction and optimization.
  • Mesh Deformations - Transforms 3D meshes into target shapes by optimizing vertex positions through gradient descent.
  • Textured Mesh Optimizations - Optimizes surface textures and color maps of 3D models to match target reference images.

Star history

Star history chart for daniilidis-group/neural_rendererStar history chart for daniilidis-group/neural_renderer

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Projects sharing features with Neural Renderer

These projects share indexed features with Neural Renderer. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • facebookresearch/pytorch3dfacebookresearch avatar

    facebookresearch/pytorch3d

    9,902View on GitHub↗

    PyTorch3D is a 3D geometric deep learning library and mesh processing toolkit designed for learning from point clouds and complex 3D surface geometries. It provides a collection of reusable components and data structures for deep learning with 3D data, including a framework for training and evaluating neural radiance fields to enable photorealistic view synthesis. The project features a differentiable 3D renderer that converts meshes and point clouds into 2D images while allowing gradients to flow back into the geometry and textures. This enables 3D shape optimization, where mesh geometry, te

    Python
    View on GitHub↗9,902
  • mitsuba-renderer/mitsuba2mitsuba-renderer avatar

    mitsuba-renderer/mitsuba2

    2,069View on GitHub↗

    Mitsuba 2 is a physically based ray tracing engine and differentiable rendering framework designed to simulate realistic light transport and compute exact gradients of the rendering process with respect to scene parameters. The software functions as an optical simulation tool that models complex phenomena using monochromatic, RGB, or spectral color representations alongside optional polarization effects. The system incorporates an automatic differentiation engine that records mathematical operations during the rendering pass to solve inverse problems and optimize designs. A plugin-based scen

    C++
    View on GitHub↗2,069
  • nvidiagameworks/kaolinNVIDIAGameWorks avatar

    NVIDIAGameWorks/kaolin

    5,107View on GitHub↗

    Kaolin is a PyTorch 3D deep learning library providing a comprehensive suite of tools for 3D geometry processing, physics simulation, data visualization, and gradient-based rendering for computer vision. The library includes a differentiable 3D renderer and a geometry processing toolkit for converting and transforming 3D representations such as meshes and point clouds. It also features a 3D physics simulation engine to calculate physical interactions and collisions between three-dimensional objects and scenes. The toolkit provides utilities for 3D data visualization, including the creation o

    Python
    View on GitHub↗5,107
  • cdcseacave/openmvscdcseacave avatar

    cdcseacave/openMVS

    4,021View on GitHub↗

    openMVS is a multi-view stereo library and photogrammetry pipeline used for 3D scene reconstruction. It transforms Structure from Motion data—specifically camera poses and sparse point clouds—into detailed 3D models consisting of dense point clouds and textured meshes. The project provides a sequence of processing stages to densify point clouds, generate 3D surface meshes, and apply photorealistic textures. It uses multi-view texture blending to map accurate colors onto reconstructed geometry and employs iterative refinement to optimize mesh details. The system includes capabilities for impo

    C++3d-reconstructiondense-point-clouddense-reconstruction
    View on GitHub↗4,021
Compare all 30 related projects→

Frequently asked questions

What does daniilidis-group/neural_renderer do?

Neural renderer is a differentiable rendering library for PyTorch that projects three-dimensional meshes into two-dimensional images while maintaining continuous mathematical gradients for backpropagation. The framework enables gradient-based inverse rendering, allowing optimization of input parameters such as camera pose, vertex positions, and texture maps by propagating pixel-level reconstruction errors backward to the source geometry.

What are the main features of daniilidis-group/neural_renderer?

The main features of daniilidis-group/neural_renderer are: Differentiable Rendering, Image-Based 3D Reconstructions, PyTorch Tensor Operations, Inverse Rendering Frameworks, Differentiable Renderers, Differentiable Shape Optimization, Camera Pose Estimators, Mesh Deformations.

Which projects share features with daniilidis-group/neural_renderer?

Projects with overlapping indexed features include: facebookresearch/pytorch3d — PyTorch3D is a 3D geometric deep learning library and mesh processing toolkit designed for learning from point clouds… nvidiagameworks/kaolin — Kaolin is a PyTorch 3D deep learning library providing a comprehensive suite of tools for 3D geometry processing,… mitsuba-renderer/mitsuba2 — Mitsuba 2 is a physically based ray tracing engine and differentiable rendering framework designed to simulate… cdcseacave/openmvs — openMVS is a multi-view stereo library and photogrammetry pipeline used for 3D scene reconstruction. It transforms… nerfstudio-project/nerfstudio — Nerfstudio is a modular development framework for training, visualizing, and exporting three-dimensional scene… nv-tlabs/get3d — GET3D is a generative 3D mesh model and rendering framework designed to synthesize high-quality textured shapes and…

Curated searches featuring Neural Renderer

Hand-picked collections where Neural Renderer appears.
  • Multi-view rendering