# ReFrame: Layer Caching for Accelerated Inference in Real-Time Rendering

arXiv: https://arxiv.org/abs/2506.13814 · HTML: https://mlsanity.com/paper/2506.13814/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 14 Jun 2025.

## Builds on (most cited first, 22 of 22)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [DeepCache: Accelerating Diffusion Models for Free](https://mlsanity.com/paper/2312.00858/) (2023)
- [Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation](https://mlsanity.com/paper/1404.0736/) (2014)
- [Cache Me if You Can: Accelerating Diffusion Models through Block Caching](https://mlsanity.com/paper/2312.03209/) (2023)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://mlsanity.com/paper/2208.14743/) (2022)
- [DeepCache: Principled Cache for Mobile Deep Vision](https://mlsanity.com/paper/1712.01670/) (2017)
- [Random-Access Neural Compression of Material Textures](https://mlsanity.com/paper/2305.17105/) (2023)
- [DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos](https://mlsanity.com/paper/2203.03996/) (2022)
- [Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers](https://mlsanity.com/paper/2308.13494/) (2023)
- [FuseSR: Super Resolution for Real-time Rendering through Efficient Multi-resolution Fusion](https://mlsanity.com/paper/2310.09726/) (2023)
- [Event Neural Networks](https://mlsanity.com/paper/2112.00891/) (2021)
- [MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos](https://mlsanity.com/paper/2210.09887/) (2022)
- [Virtual Occlusions Through Implicit Depth](https://mlsanity.com/paper/2305.07014/) (2023)
- [FlexCache: Flexible Approximate Cache System for Video Diffusion](https://mlsanity.com/paper/2501.04012/) (2024)
- [Efficient neural supersampling on a novel gaming dataset](https://mlsanity.com/paper/2308.01483/) (2023)
- [Low-latency Space-time Supersampling for Real-time Rendering](https://mlsanity.com/paper/2312.10890/) (2023)
- [RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing](https://mlsanity.com/paper/2310.03507/) (2023)

## Abstract (arXiv)

Graphics rendering applications increasingly leverage neural networks in tasks such as denoising, supersampling, and frame extrapolation to improve image quality while maintaining frame rates. The temporal coherence inherent in these tasks presents an opportunity to reuse intermediate results from previous frames and avoid redundant computations. Recent work has shown that caching intermediate features to be reused in subsequent inferences is an effective method to reduce latency in diffusion models. We extend this idea to real-time rendering and present ReFrame, which explores different caching policies to optimize trade-offs between quality and performance in rendering workloads. ReFrame can be applied to a variety of encoder-decoder style networks commonly found in rendering pipelines. Experimental results show that we achieve 1.4x speedup on average with negligible quality loss in three real-time rendering tasks. Code available: https://ubc-aamodt-group.github.io/reframe-layer-caching/