paper-with-me

홈 › Papers

Aligning Motion-Blurred Images Using Contrastive Learning on Overcomplete Pixels

2024-10-09 · Leonid Pogorelyuk, Stefan T. Radev

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.

📄 PDF Abstract BibTeX arXiv:2410.07410

Code (1)

leonidprinceton/oxels 공식 구현 tf

Tasks

Contrastive Learning

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Stable Single-Pixel Contrastive Learning for Semantic and Geometric Tasks

2025-12-04 · Leonid Pogorelyuk, Niels Bracher, Aaron Verkleeren, Lars Kühmichel 외 arxiv

We pilot a family of stable contrastive losses for learning pixel-level representations that jointly capture semantic and geometric information. Our approach maps each pixel of an image to an overcomplete descriptor that…

Contrastive Learning

Learning to Synthesize Motion Blur

2018-11-27 · CVPR 2019 6 · Tim Brooks, Jonathan T. Barron

We present a technique for synthesizing a motion blurred image from a pair of unblurred images captured in succession. To build this system we motivate and design a differentiable "line prediction" layer to be used as pa…

Rethinking Motion Deblurring Training: A Segmentation-Based Method for Simulating Non-Uniform Motion Blurred Images

2022-09-26 · Guillermo Carbajal, Patricia Vitoria, Pablo Musé, José Lezama

Successful training of end-to-end deep networks for real motion deblurring requires datasets of sharp/blurred image pairs that are realistic and diverse enough to achieve generalization to real blurred images. Obtaining …

Deblurring

ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images

2023-09-16 · ICCV 2023 1 · Dongwoo Lee, Jeongtaek Oh, Jaesung Rim, Sunghyun Cho 외

We present ExBluRF, a novel view synthesis method for extreme motion blurred images based on efficient radiance fields optimization. Our approach consists of two main components: 6-DOF camera trajectory-based motion blur…

GPUNovel View Synthesis

Multi-Focus Image Fusion Using Sparse Representation and Coupled Dictionary Learning

2017-05-30 · Farshad G. Veshki, Sergiy A. Vorobyov

We address the multi-focus image fusion problem, where multiple images captured with different focal settings are to be fused into an all-in-focus image of higher quality. Algorithms for this problem necessarily admit th…

Dictionary LearningMulti Focus Image Fusion