English
Related papers

Related papers: Deep Lambertian Networks

200 papers

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We…

Computer Vision and Pattern Recognition · Computer Science 2020-09-02 Shuyu Lin , Ronald Clark

We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local…

Machine Learning · Computer Science 2019-07-09 Philip Bachman , R Devon Hjelm , William Buchwalter

High-quality facial appearance capture has traditionally required costly studio recording. Recent works consider an in-the-wild smartphone-based setup; however, their model-based inverse rendering paradigm struggles with the complex…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Yuxuan Han , Xin Ming , Tianxiao Li , Zhuofan Shen , Qixuan Zhang , Lan Xu , Feng Xu

Dense prediction tasks typically employ encoder-decoder architectures, but the prevalent convolutions in the decoder are not image-adaptive and can lead to boundary artifacts. Different generalized convolution operations have been…

Computer Vision and Pattern Recognition · Computer Science 2019-09-10 Anne S. Wannenwetsch , Martin Kiefel , Peter V. Gehler , Stefan Roth

Latent representations are the essence of deep generative models and determine their usefulness and power. For latent representations to be useful as generative concept representations, their latent space must support latent space…

Machine Learning · Computer Science 2019-01-01 Daniel T. Chang

Occupancy prediction aims to estimate the 3D spatial distribution of occupied regions along with their corresponding semantic labels. Existing vision-based methods perform well on daytime benchmarks but struggle in nighttime scenarios due…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Yuan Wu , Zhiqiang Yan , Yigong Zhang , Xiang Li , Jian Yang

Dynamic multilayer networks frequently represent the structure of multiple co-evolving relations; however, statistical models are not well-developed for this prevalent network type. Here, we propose a new latent space model for dynamic…

Methodology · Statistics 2021-03-25 Joshua Daniel Loyal , Yuguo Chen

While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects. This limits the use of depth prediction in augmented and virtual…

Computer Vision and Pattern Recognition · Computer Science 2019-05-09 Helisa Dhamo , Keisuke Tateno , Iro Laina , Nassir Navab , Federico Tombari

While deep learning methods have achieved state-of-the-art performance in many challenging inverse problems like image inpainting and super-resolution, they invariably involve problem-specific training of the networks. Under this approach,…

Computer Vision and Pattern Recognition · Computer Science 2017-03-30 J. H. Rick Chang , Chun-Liang Li , Barnabas Poczos , B. V. K. Vijaya Kumar , Aswin C. Sankaranarayanan

Over the last decade, robotic perception algorithms have significantly benefited from the rapid advances in deep learning (DL). Indeed, a significant amount of the autonomy stack of different commercial and research platforms relies on DL…

Robotics · Computer Science 2022-03-09 Yu Xianjia , Sahar Salimpour , Jorge Peña Queralta , Tomi Westerlund

The paradigm shift from shallow classifiers with hand-crafted features to end-to-end trainable deep learning models has shown significant improvements on supervised learning tasks. Despite the promising power of deep neural networks (DNN),…

Machine Learning · Computer Science 2017-06-09 Chih-Kuan Yeh , Yao-Hung Hubert Tsai , Yu-Chiang Frank Wang

Machine learning based Single Image Intrinsic Decomposition (SIID) methods decompose a captured scene into its albedo and shading images by using the knowledge of a large set of known and realistic ground truth decompositions. Collecting…

Computer Vision and Pattern Recognition · Computer Science 2018-09-05 Louis Lettry , Kenneth Vanhoey , Luc van Gool

This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Yinglong Wang , Zhen Liu , Jianzhuang Liu , Songcen Xu , Shuaicheng Liu

Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Titus Leistner , Radek Mackowiak , Lynton Ardizzone , Ullrich Köthe , Carsten Rother

Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network…

Machine Learning · Computer Science 2019-07-17 Shuhao Xia , Yuanming Shi

There are many real-world knowledge based networked systems with multi-type interacting entities that can be regarded as heterogeneous networks including human connections and biological evolutions. One of the main issues in such networks…

Social and Information Networks · Computer Science 2019-11-05 Soheila Molaei , Hadi Zare , Hadi Veisi

Aberrations limit optical systems in many situations, for example when imaging in biological tissue. Machine learning offers novel ways to improve imaging under such conditions by learning inverse models of aberrations. Learning requires…

Optics · Physics 2021-04-30 Ivan Vishniakou , Johannes D. Seelig

As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-03-07 John Day , Tushar Arora , Jirui Liu , Li Erran Li , Ming Bo Cai

There is an increasing interest in using image-generating diffusion models for deep data augmentation and image morphing. In this context, it is useful to interpolate between latents produced by inverting a set of input images, in order to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Erik Landolsi , Fredrik Kahl

A central problem in unsupervised domain adaptation is determining what to transfer from labeled source domains to an unlabeled target domain. To handle high-dimensional observations (e.g., images), a line of approaches use deep learning to…

Machine Learning · Computer Science 2026-04-28 Ignavier Ng , Yan Li , Zijian Li , Yujia Zheng , Guangyi Chen , Kun Zhang