# DeLiVR: Differential Spatiotemporal Lie Bias for Efficient Video Deraining

arXiv: https://arxiv.org/abs/2509.21719 · HTML: https://mlsanity.com/paper/2509.21719/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 41 references that are in the map.
- First posted on arXiv 26 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [Recurrent Video Restoration Transformer with Guided Deformable Attention](https://mlsanity.com/paper/2206.02146/) (2022)
- [A Model-driven Deep Neural Network for Single Image Rain Removal](https://mlsanity.com/paper/2005.01333/) (2020)
- [LieTransformer: Equivariant self-attention for Lie Groups](https://mlsanity.com/paper/2012.10885/) (2020)
- [RainMamba: Enhanced Locality Learning with State Space Models for Video Deraining](https://mlsanity.com/paper/2407.21773/) (2024)
- [Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework](https://mlsanity.com/paper/1803.10433/) (2018)
- [From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal](https://mlsanity.com/paper/2308.03867/) (2023)
- [Semi-Supervised Video Deraining with Dynamical Rain Generator](https://mlsanity.com/paper/2103.07939/) (2021)
- [Revisiting Temporal Alignment for Video Restoration](https://mlsanity.com/paper/2111.15288/) (2021)
- [Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation](https://mlsanity.com/paper/2309.13700/) (2023)
- [WeatherBench: A Real-World Benchmark Dataset for All-in-One Adverse Weather Image Restoration](https://mlsanity.com/paper/2509.11642/) (2025)
- [Rain Removal in Traffic Surveillance: Does it Matter?](https://mlsanity.com/paper/1810.12574/) (2018)
- [Learning Truncated Causal History Model for Video Restoration](https://mlsanity.com/paper/2410.03936/) (2024)
- [Unsupervised Image Deraining: Optimization Model Driven Deep CNN](https://mlsanity.com/paper/2203.13699/) (2022)
- [Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining](https://mlsanity.com/paper/2505.16811/) (2025)
- [DiTVR: Zero-Shot Diffusion Transformer for Video Restoration](https://mlsanity.com/paper/2508.07811/) (2025)
- [Towards Better De-raining Generalization via Rainy Characteristics Memorization and Replay](https://mlsanity.com/paper/2506.02477/) (2025)

## Built on by (most cited first, 4 of 4)

- [RainDancer: RGB-Event Video Deraining with Rain-Oriented Spiking Dynamics](https://mlsanity.com/paper/2607.13802/) (2026)
- [Revisiting the Current Frame: Physical-Trace-Guided Network Output Correction for Video Restoration](https://mlsanity.com/paper/2608.09342/) (2026)
- [S3VD: Semantic-Guidance Spatio-Temporal Scanning for Video Deraining](https://mlsanity.com/paper/2609.21322/) (2026)
- [FluidRain: Incompressible Rain Flow as an Attention Bias for Loop-in-Loop Video Deraining](https://mlsanity.com/paper/2609.29006/) (2026)

## Abstract (arXiv)

Videos captured in the wild often suffer from rain streaks, blur, and noise. In addition, even slight changes in camera pose can amplify cross-frame mismatches and temporal artifacts. Existing methods rely on optical flow or heuristic alignment, which are computationally expensive and less robust. To address these challenges, Lie groups provide a principled way to represent continuous geometric transformations, making them well-suited for enforcing spatial and temporal consistency in video modeling. Building on this insight, we propose DeLiVR, an efficient video deraining method that injects spatiotemporal Lie-group differential biases directly into attention scores of the network. Specifically, the method introduces two complementary components. First, a rotation-bounded Lie relative bias predicts the in-plane angle of each frame using a compact prediction module, where normalized coordinates are rotated and compared with base coordinates to achieve geometry-consistent alignment before feature aggregation. Second, a differential group displacement computes angular differences between adjacent frames to estimate a velocity. This bias computation combines temporal decay and attention masks to focus on inter-frame relationships while precisely matching the direction of rain streaks. Extensive experimental results demonstrate the effectiveness of our method on publicly available benchmarks. The code is publicly available at https://github.com/Shuning0312/ICLR-DeLiVR.