English
Related papers

Related papers: Model-based occlusion disentanglement for image-to…

200 papers

Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions…

Computer Vision and Pattern Recognition · Computer Science 2023-03-06 Fei Wang , Jun Cheng , Penglei Liu

There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components. We demonstrate that one of…

Computation and Language · Computer Science 2022-03-23 Hao Zheng , Mirella Lapata

We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested classification…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 David Berga , Marc Masana , Joost Van de Weijer

Deep neural networks have been applied successfully to a wide variety of inverse problems arising in computational imaging. These networks are typically trained using a forward model that describes the measurement process to be inverted,…

Image and Video Processing · Electrical Eng. & Systems 2021-04-14 Davis Gilton , Gregory Ongie , Rebecca Willett

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…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Leonid Pogorelyuk , Stefan T. Radev

Recent object detectors have achieved impressive accuracy in identifying objects seen during training. However, real-world deployment often introduces novel and unexpected objects, referred to as out-of-distribution (OOD) objects, posing…

Machine Learning · Computer Science 2025-11-20 Quang-Huy Nguyen , Jin Peng Zhou , Zhenzhen Liu , Khanh-Huyen Bui , Kilian Q. Weinberger , Wei-Lun Chao , Dung D. Le

We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency while supporting large appearance changes during unpaired image-to-image (I2I) translation. Previous…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Chuanxia Zheng , Tat-Jen Cham , Jianfei Cai

Image classification models, including convolutional neural networks (CNNs), perform well on a variety of classification tasks but struggle under conditions of partial occlusion, i.e., conditions in which objects are partially covered from…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Kaleb Kassaw , Francesco Luzi , Leslie M. Collins , Jordan M. Malof

The acquisition of objects outside the Line-of-Sight of cameras is a very intriguing but also extremely challenging research topic. Recent works showed the feasibility of this idea exploiting transient imaging data produced by custom direct…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Matteo Caligiuri , Adriano Simonetto , Pietro Zanuttigh

We address the problem of camera pose estimation in visual localization. Current regression-based methods for pose estimation are trained and evaluated scene-wise. They depend on the coordinate frame of the training dataset and show a low…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Boris Chidlovskii , Assem Sadek

Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Sanket Gandhi , Atul , Samanyu Mahajan , Vishal Sharma , Rushil Gupta , Arnab Kumar Mondal , Parag Singla

Diffusion models have dramatically advanced text-to-image generation in recent years, translating abstract concepts into high-fidelity images with remarkable ease. In this work, we examine whether they can also blend distinct concepts,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Lorenzo Olearo , Giorgio Longari , Alessandro Raganato , Rafael Peñaloza , Simone Melzi

Text-to-image diffusion models have made significant progress in generating naturalistic images from textual inputs, and demonstrate the capacity to learn and represent complex visual-semantic relationships. While these diffusion models…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Rushikesh Zawar , Shaurya Dewan , Prakanshul Saxena , Yingshan Chang , Andrew Luo , Yonatan Bisk

A core challenge in Machine Learning is to learn to disentangle natural factors of variation in data (e.g. object shape vs. pose). A popular approach to disentanglement consists in learning to map each of these factors to distinct subspaces…

Machine Learning · Computer Science 2021-02-11 Diane Bouchacourt , Mark Ibrahim , Stéphane Deny

Developing meaningful and efficient representations that separate the fundamental structure of the data generation mechanism is crucial in representation learning. However, Disentangled Representation Learning has not fully shown its…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Jacopo Dapueto , Nicoletta Noceti , Francesca Odone

Unpaired Image-to-image Translation is a new rising and challenging vision problem that aims to learn a mapping between unaligned image pairs in diverse domains. Recent advances in this field like MUNIT and DRIT mainly focus on…

Computer Vision and Pattern Recognition · Computer Science 2019-05-07 Zhiqiang Shen , Mingyang Huang , Jianping Shi , Xiangyang Xue , Thomas Huang

We present a method that tackles the challenge of predicting color and depth behind the visible content of an image. Our approach aims at building up a Layered Depth Image (LDI) from a single RGB input, which is an efficient representation…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Helisa Dhamo , Nassir Navab , Federico Tombari

Image blending is an integral part of many multi-image applications such as panorama stitching or remote image acquisition processes. In such scenarios, multiple images are connected at predefined boundaries to form a larger image. A…

Image and Video Processing · Electrical Eng. & Systems 2023-05-11 Paul Bungert , Pascal Peter , Joachim Weickert

It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised…

Computer Vision and Pattern Recognition · Computer Science 2018-04-05 Yang Wang , Yi Yang , Zhenheng Yang , Liang Zhao , Peng Wang , Wei Xu

Unsupervised learning enables modeling complex images without the need for annotations. The representation learned by such models can facilitate any subsequent analysis of large image datasets. However, some generative factors that cause…

Image and Video Processing · Electrical Eng. & Systems 2020-08-27 Maxime W. Lafarge , Josien P. W. Pluim , Mitko Veta
‹ Prev 1 8 9 10 Next ›