# In-Loop Filtering via Trained Look-Up Tables

arXiv: https://arxiv.org/abs/2407.10926 · HTML: https://mlsanity.com/paper/2407.10926/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 40 references that are in the map.
- First posted on arXiv 15 Jul 2024.

## Builds on (most cited first, 11 of 11)

- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [BVI-DVC: A Training Database for Deep Video Compression](https://mlsanity.com/paper/2003.13552/) (2020)
- [AdderSR: Towards Energy Efficient Image Super-Resolution](https://mlsanity.com/paper/2009.08891/) (2020)
- [A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding](https://mlsanity.com/paper/1608.06690/) (2016)
- [Object Segmentation-Assisted Inter Prediction for Versatile Video Coding](https://mlsanity.com/paper/2403.11694/) (2024)
- [Deep Learning-Based Video Coding: A Review and A Case Study](https://mlsanity.com/paper/1904.12462/) (2019)
- [Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution](https://mlsanity.com/paper/2307.08544/) (2023)
- [Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables](https://mlsanity.com/paper/2303.14506/) (2023)
- [Convolutional Neural Network-Based Block Up-sampling for Intra Frame Coding](https://mlsanity.com/paper/1702.06728/) (2017)
- [Online Streaming Video Super-Resolution with Convolutional Look-Up Table](https://mlsanity.com/paper/2303.00334/) (2023)
- [Designs and Implementations in Neural Network-based Video Coding](https://mlsanity.com/paper/2309.05846/) (2023)

## Built on by (most cited first, 8 of 8)

- [Learned Image Compression with Hierarchical Progressive Context Modeling](https://mlsanity.com/paper/2507.19125/) (2025)
- [Neural B-frame Video Compression with Bi-directional Reference Harmonization](https://mlsanity.com/paper/2511.08938/) (2025)
- [Retinex-MEF: Retinex-based Glare Effects Aware Unsupervised Multi-Exposure Image Fusion](https://mlsanity.com/paper/2503.07235/) (2025)
- [Scaling Learned Image Compression Models up to 1 Billion](https://mlsanity.com/paper/2508.09075/) (2025)
- [In-Loop Filtering Using Learned Look-Up Tables for Video Coding](https://mlsanity.com/paper/2509.09494/) (2025)
- [Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Tasks](https://mlsanity.com/paper/2510.10522/) (2025)
- [Uncertainty-aware Spatial-Frequency Registration and Fusion for Infrared and Visible Images](https://mlsanity.com/paper/2605.13049/) (2026)
- [Latent Lie-Poisson Neural Networks (LLPNNs): Discovering the motion of Lie-Poisson systems through observable data and latent dynamics](https://mlsanity.com/paper/2607.28939/) (2026)

## Abstract (arXiv)

In-loop filtering (ILF) is a key technology for removing the artifacts in image/video coding standards. Recently, neural network-based in-loop filtering methods achieve remarkable coding gains beyond the capability of advanced video coding standards, which becomes a powerful coding tool candidate for future video coding standards. However, the utilization of deep neural networks brings heavy time and computational complexity, and high demands of high-performance hardware, which is challenging to apply to the general uses of coding scene. To address this limitation, inspired by explorations in image restoration, we propose an efficient and practical in-loop filtering scheme by adopting the Look-up Table (LUT). We train the DNN of in-loop filtering within a fixed filtering reference range, and cache the output values of the DNN into a LUT via traversing all possible inputs. At testing time in the coding process, the filtered pixel is generated by locating input pixels (to-be-filtered pixel with reference pixels) and interpolating cached filtered pixel values. To further enable the large filtering reference range with the limited storage cost of LUT, we introduce the enhanced indexing mechanism in the filtering process, and clipping/finetuning mechanism in the training. The proposed method is implemented into the Versatile Video Coding (VVC) reference software, VTM-11.0. Experimental results show that the ultrafast, very fast, and fast mode of the proposed method achieves on average 0.13%/0.34%/0.51%, and 0.10%/0.27%/0.39% BD-rate reduction, under the all intra (AI) and random access (RA) configurations. Especially, our method has friendly time and computational complexity, only 101%/102%-104%/108% time increase with 0.13-0.93 kMACs/pixel, and only 164-1148 KB storage cost for a single model. Our solution may shed light on the journey of practical neural network-based coding tool evolution.