# Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete Pixels

arXiv: https://arxiv.org/abs/2410.07410 · HTML: https://mlsanity.com/paper/2410.07410/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [GMFlow: Learning Optical Flow via Global Matching](https://mlsanity.com/paper/2111.13680/) (2021)
- [COTR: Correspondence Transformer for Matching Across Images](https://mlsanity.com/paper/2103.14167/) (2021)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Deep Learning-based Spacecraft Relative Navigation Methods: A Survey](https://mlsanity.com/paper/2108.08876/) (2021)
- [Exploring Overcomplete Representations for Single Image Deraining using CNNs](https://mlsanity.com/paper/2010.10661/) (2020)
- [Overcomplete Deep Subspace Clustering Networks](https://mlsanity.com/paper/2011.08306/) (2020)
- [Effective learning is accompanied by high dimensional and efficient representations of neural activity](https://mlsanity.com/paper/1709.10045/) (2017)

## Built on by (most cited first, 1 of 1)

- [Stable Single-Pixel Contrastive Learning for Semantic and Geometric Tasks](https://mlsanity.com/paper/2512.04970/) (2025)

## Abstract (arXiv)

We propose a new contrastive objective for learning overcomplete pixel-level features that are invariant to motion blur. Other invariances (e.g., pose, illumination, or weather) can be learned by applying the corresponding transformations on unlabeled images during self-supervised training. We showcase that a simple U-Net trained with our objective can produce local features useful for aligning the frames of an unseen video captured with a moving camera under realistic and challenging conditions. Using a carefully designed toy example, we also show that the overcomplete pixels can encode the identity of objects in an image and the pixel coordinates relative to these objects.