# Fast and Accurate Neural Rendering Using Semi-Gradients

arXiv: https://arxiv.org/abs/2410.10149 · HTML: https://mlsanity.com/paper/2410.10149/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 35 references that are in the map.
- First posted on arXiv 14 Oct 2024.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [Neural Radiosity](https://mlsanity.com/paper/2105.12319/) (2021)
- [Deep Residual Reinforcement Learning](https://mlsanity.com/paper/1905.01072/) (2019)
- [Adam^+: A Stochastic Method with Adaptive Variance Reduction](https://mlsanity.com/paper/2011.11985/) (2020)
- [Plateau-reduced Differentiable Path Tracing](https://mlsanity.com/paper/2211.17263/) (2022)
- [Inverse Global Illumination using a Neural Radiometric Prior](https://mlsanity.com/paper/2305.02192/) (2023)
- [Toward Efficient Gradient-Based Value Estimation](https://mlsanity.com/paper/2301.13757/) (2023)
- [An Experimental Comparison Between Temporal Difference and Residual Gradient with Neural Network Approximation](https://mlsanity.com/paper/2205.12770/) (2022)

## Abstract (arXiv)

We propose a simple yet effective neural network-based framework for global illumination rendering. Recently, rendering techniques that learn neural radiance caches by minimizing the difference (i.e., residual) between the left and right sides of the rendering equation have been suggested. Due to their ease of implementation and the advantage of excluding path integral calculations, these techniques have been applied to various fields, such as free-viewpoint rendering, differentiable rendering, and real-time rendering. However, issues of slow training and occasionally darkened renders have been noted. We identify the cause of these issues as the bias and high variance present in the gradient estimates of the existing residual-based objective function. To address this, we introduce a new objective function that maintains the same global optimum as before but allows for unbiased and low-variance gradient estimates, enabling faster and more accurate training of neural networks. In conclusion, this method is simply implemented by ignoring the partial derivatives of the right-hand side, and theoretical and experimental analyses demonstrate the effectiveness of the proposed loss.