# Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering

arXiv: https://arxiv.org/abs/2202.01284 · HTML: https://mlsanity.com/paper/2202.01284/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Feb 2022.

## Built on by (most cited first, 16 of 16)

- [Adaptive Shells for Efficient Neural Radiance Field Rendering](https://mlsanity.com/paper/2311.10091/) (2023)
- [PhysGen3D: Crafting a Miniature Interactive World from a Single Image](https://mlsanity.com/paper/2503.20746/) (2025)
- [High-Res Facial Appearance Capture from Polarized Smartphone Images](https://mlsanity.com/paper/2212.01160/) (2022)
- [N-Dimensional Gaussians for Fitting of High Dimensional Functions](https://mlsanity.com/paper/2405.20067/) (2024)
- [NeRF as a Non-Distant Environment Emitter in Physics-based Inverse Rendering](https://mlsanity.com/paper/2402.04829/) (2024)
- [Differentiable Visual Computing for Inverse Problems and Machine Learning](https://mlsanity.com/paper/2312.04574/) (2023)
- [Diffusion Posterior Illumination for Ambiguity-aware Inverse Rendering](https://mlsanity.com/paper/2310.00362/) (2023)
- [Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation](https://mlsanity.com/paper/2409.10071/) (2024)
- [Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphics](https://mlsanity.com/paper/2308.05739/) (2023)
- [Differentiable Shadow Mapping for Efficient Inverse Graphics](https://mlsanity.com/paper/2308.10896/) (2023)
- [SwarmRL: Building the Future of Smart Active Systems](https://mlsanity.com/paper/2404.16388/) (2024)
- [Neural Product Importance Sampling via Warp Composition](https://mlsanity.com/paper/2409.18974/) (2024)
- [Example-Based Sampling with Diffusion Models](https://mlsanity.com/paper/2302.05116/) (2023)
- [DiffRenderGAN: Addressing Training Data Scarcity in Deep Segmentation Networks for Quantitative Nanomaterial Analysis through Differentiable Rendering and Generative Modelling](https://mlsanity.com/paper/2502.09477/) (2025)
- [A Modularized Design Approach for GelSight Family of Vision-based Tactile Sensors](https://mlsanity.com/paper/2504.14739/) (2025)
- [Automated design of compound lenses with discrete-continuous optimization](https://mlsanity.com/paper/2509.23572/) (2025)

## Abstract (arXiv)

Dr.Jit is a new just-in-time compiler for physically based rendering and its derivative. Dr.Jit expedites research on these topics in two ways: first, it traces high-level simulation code (e.g., written in Python) and aggressively simplifies and specializes the resulting program representation, producing data-parallel kernels with state-of-the-art performance on CPUs and GPUs. Second, it simplifies the development of differentiable rendering algorithms. Efficient methods in this area turn the derivative of a simulation into a simulation of the derivative. Dr.Jit provides fine-grained control over the process of automatic differentiation to help with this transformation. Specialization is particularly helpful in the context of differentiation, since large parts of the simulation ultimately do not influence the computed gradients. Dr.Jit tracks data dependencies globally to find and remove redundant computation.