A PyTorch Library for Accelerating 3D Deep Learning Research

Project page of paper "Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning"

Differentiable rendering without approximation.

3D mesh stylization driven by a text input in PyTorch

Point-NeRF: Point-based Neural Radiance Fields

Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer (NeurIPS 2019)

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"

Project Page of 'GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction' [CVPR2019]

DIRT: a fast differentiable renderer for TensorFlow

SVG Differentiable Rendering: Generating vector graphics using neural networks. Support: text-to-SVG, Image-to-SVG, SVG Editing.

Auto-differentiable digitally reconstructed radiographs in PyTorch

Automated lens design from scratch.

Differentiable Surface Splatting

Official Pytorch Implementation of 3DV2021 paper: SAFA: Structure Aware Face Animation.

A framework for 4D reconstruction from monocular videos.

A differentiable 3D renderer with Pytorch, Tensorflow and Matlab interfaces

[SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction

Multi-View Mesh Reconstruction with Neural Deferred Shading (CVPR 2022)

[CVPR 2021 - Oral] UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering