# BOCCHI: A More Realistic and Challenging Benchmark for Local Motion Blur Detection with MSDCT-UNet

arXiv: https://arxiv.org/abs/2607.10427 · HTML: https://mlsanity.com/paper/2607.10427/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 53 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Builds on (most cited first, 30 of 31)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation](https://mlsanity.com/paper/2004.02147/) (2020)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal](https://mlsanity.com/paper/1503.00593/) (2015)
- [Stripformer: Strip Transformer for Fast Image Deblurring](https://mlsanity.com/paper/2204.04627/) (2022)
- [Fast-SCNN: Fast Semantic Segmentation Network](https://mlsanity.com/paper/1902.04502/) (2019)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blur](https://mlsanity.com/paper/1612.02583/) (2016)
- [Adaptive Frequency Filters As Efficient Global Token Mixers](https://mlsanity.com/paper/2307.14008/) (2023)
- [Real-World Deep Local Motion Deblurring](https://mlsanity.com/paper/2204.08179/) (2022)
- [Spatially-Varying Blur Detection Based on Multiscale Fused and Sorted Transform Coefficients of Gradient Magnitudes](https://mlsanity.com/paper/1703.07478/) (2017)
- [Defocus Blur Detection via Depth Distillation](https://mlsanity.com/paper/2007.08113/) (2020)
- [Learning to Control Camera Exposure via Reinforcement Learning](https://mlsanity.com/paper/2404.01636/) (2024)
- [AlignSAM: Aligning Segment Anything Model to Open Context via Reinforcement Learning](https://mlsanity.com/paper/2406.00480/) (2024)
- [Adaptive Window Pruning for Efficient Local Motion Deblurring](https://mlsanity.com/paper/2306.14268/) (2023)
- [Dense Dual-Path Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/2010.10778/) (2020)
- [RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes](https://mlsanity.com/paper/2601.05249/) (2026)

## Abstract (arXiv)

Local motion blur detection requires pixel-level localization of blurred regions. Existing benchmarks let models rely on gradient shortcuts that fail to transfer. We introduce BOCCHI (Blurred Objects Captured across Cameras with Human-annotated Imagery), a real-captured benchmark whose sharp regions overlap the blur gradient distribution and defeat these shortcuts, and propose MSDCT-UNet (Multi-Scale Discrete Cosine Transform UNet), a frequency-aware encoder-decoder injecting multi-scale DCT priors through DCT Attention and FiLM. MSDCT-UNet ranks first in in-domain mIoU and boundary localization on BOCCHI, and BOCCHI-trained models outperform every other training source on cross-dataset transfer with only 633 training images. Our project page is available at https://brianchen1120.github.io/project/bocchi/.