# DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelines

arXiv: https://arxiv.org/abs/2401.05345 · HTML: https://mlsanity.com/paper/2401.05345/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 69 references that are in the map.
- First posted on arXiv 1 Dec 2023.

## Builds on (most cited first, 30 of 33)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021)
- [Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields](https://mlsanity.com/paper/2304.06706/) (2023)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [FastNeRF: High-Fidelity Neural Rendering at 200FPS](https://mlsanity.com/paper/2103.10380/) (2021)
- [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021)
- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures](https://mlsanity.com/paper/2208.00277/) (2022)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks](https://mlsanity.com/paper/2103.03231/) (2021)
- [Drivable 3D Gaussian Avatars](https://mlsanity.com/paper/2311.08581/) (2023)
- [NerfAcc: Efficient Sampling Accelerates NeRFs](https://mlsanity.com/paper/2305.04966/) (2023)
- [Improved Direct Voxel Grid Optimization for Radiance Fields Reconstruction](https://mlsanity.com/paper/2206.05085/) (2022)
- [Imitating Interactive Intelligence](https://mlsanity.com/paper/2012.05672/) (2020)
- [Instant-3D: Instant Neural Radiance Field Training Towards On-Device AR/VR 3D Reconstruction](https://mlsanity.com/paper/2304.12467/) (2023)
- [RT-NeRF: Real-Time On-Device Neural Radiance Fields Towards Immersive AR/VR Rendering](https://mlsanity.com/paper/2212.01120/) (2022)
- [Flexible Techniques for Differentiable Rendering with 3D Gaussians](https://mlsanity.com/paper/2308.14737/) (2023)
- [Hardware Acceleration of Neural Graphics](https://mlsanity.com/paper/2303.05735/) (2023)

## Built on by (most cited first, 30 of 36)

- [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024)
- [Taming 3DGS: High-Quality Radiance Fields with Limited Resources](https://mlsanity.com/paper/2406.15643/) (2024)
- [Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives](https://mlsanity.com/paper/2412.00578/) (2024)
- [FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering](https://mlsanity.com/paper/2408.07967/) (2024)
- [3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities](https://mlsanity.com/paper/2407.17418/) (2024)
- [Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2502.20220/) (2025)
- [GGHead: Fast and Generalizable 3D Gaussian Heads](https://mlsanity.com/paper/2406.09377/) (2024)
- [3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt](https://mlsanity.com/paper/2409.12892/) (2024)
- [DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds](https://mlsanity.com/paper/2503.18402/) (2025)
- [Faster-GS: Analyzing and Improving Gaussian Splatting Optimization](https://mlsanity.com/paper/2602.09999/) (2026)
- [Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians](https://mlsanity.com/paper/2411.12788/) (2024)
- [Balanced 3DGS: Gaussian-wise Parallelism Rendering with Fine-Grained Tiling](https://mlsanity.com/paper/2412.17378/) (2024)
- [TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores](https://mlsanity.com/paper/2505.24796/) (2025)
- [QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization](https://mlsanity.com/paper/2505.05591/) (2025)
- [Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields](https://mlsanity.com/paper/2412.13547/) (2024)
- [CaRtGS: Computational Alignment for Real-Time Gaussian Splatting SLAM](https://mlsanity.com/paper/2410.00486/) (2024)
- [Plenodium: UnderWater 3D Scene Reconstruction with Plenoptic Medium Representation](https://mlsanity.com/paper/2505.21258/) (2025)
- [Duplex-GS: Proxy-Guided Weighted Blending for Real-Time Order-Independent Gaussian Splatting](https://mlsanity.com/paper/2508.03180/) (2025)
- [GS-Scale: Unlocking Large-Scale 3D Gaussian Splatting Training via Host Offloading](https://mlsanity.com/paper/2509.15645/) (2025)
- [Gaussian On-the-Fly Splatting: A Progressive Framework for Robust Near Real-Time 3DGS Optimization](https://mlsanity.com/paper/2503.13086/) (2025)
- [ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction](https://mlsanity.com/paper/2509.03775/) (2025)
- [Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists](https://mlsanity.com/paper/2603.09277/) (2026)
- [Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric](https://mlsanity.com/paper/2511.08032/) (2025)
- [Trick-GS: A Balanced Bag of Tricks for Efficient Gaussian Splatting](https://mlsanity.com/paper/2501.14534/) (2025)
- [FaCT-GS: Fast and Scalable CT Reconstruction with Gaussian Splatting](https://mlsanity.com/paper/2604.01844/) (2026)
- [BlitzGS: City-Scale Gaussian Splatting at Lightning Speed](https://mlsanity.com/paper/2605.13794/) (2026)
- [HiGS: A Hierarchical Rendering Architecture for Real-Time 3D Gaussian Splatting](https://mlsanity.com/paper/2606.00352/) (2026)
- [GSta: Efficient Training Scheme with Siestaed Gaussians for Monocular 3D Scene Reconstruction](https://mlsanity.com/paper/2504.06716/) (2025)
- [DirectFisheye-GS: Enabling Native Fisheye Input in Gaussian Splatting with Cross-View Joint Optimization](https://mlsanity.com/paper/2604.00648/) (2026)
- [Splaxel: Efficient Distributed Training of 3D Gaussian Splatting for Large-scale Scene Reconstruction via Pixel-level Communication](https://mlsanity.com/paper/2606.18588/) (2026)

## Abstract (arXiv)

Differentiable rendering is a technique used in an important emerging class of visual computing applications that involves representing a 3D scene as a model that is trained from 2D images using gradient descent. Recent works (e.g. 3D Gaussian Splatting) use a rasterization pipeline to enable rendering high quality photo-realistic imagery at high speeds from these learned 3D models. These methods have been demonstrated to be very promising, providing state-of-art quality for many important tasks. However, training a model to represent a scene is still a time-consuming task even when using powerful GPUs. In this work, we observe that the gradient computation phase during training is a significant bottleneck on GPUs due to the large number of atomic operations that need to be processed. These atomic operations overwhelm atomic units in the L2 partitions causing stalls. To address this challenge, we leverage the observations that during the gradient computation: (1) for most warps, all threads atomically update the same memory locations; and (2) warps generate varying amounts of atomic traffic (since some threads may be inactive). We propose DISTWAR, a software-approach to accelerate atomic operations based on two key ideas: First, we enable warp-level reduction of threads at the SM sub-cores using registers to leverage the locality in intra-warp atomic updates. Second, we distribute the atomic computation between the warp-level reduction at the SM and the L2 atomic units to increase the throughput of atomic computation. Warps with many threads performing atomic updates to the same memory locations are scheduled at the SM, and the rest using L2 atomic units. We implement DISTWAR using existing warp-level primitives. We evaluate DISTWAR on widely used raster-based differentiable rendering workloads. We demonstrate significant speedups of 2.44x on average (up to 5.7x).