Related papers: Excavate Condition-invariant Space by Intrinsic En…

When a human drives a car along a road for the first time, they later recognize where they are on the return journey typically without needing to look in their rear-view mirror or turn around to look back, despite significant viewpoint and…

Perceptual learning enables humans to recognize and represent stimuli invariant to various transformations and build a consistent representation of the self and physical world. Such representations preserve the invariant physical relations…

Face inpainting requires the model to have a precise global understanding of the facial position structure. Benefiting from the powerful capabilities of deep learning backbones, recent works in face inpainting have achieved decent…

Urban planning designs land-use configurations and can benefit building livable, sustainable, safe communities. Inspired by image generation, deep urban planning aims to leverage deep learning to generate land-use configurations. However,…

The character information in natural scene images contains various personal information, such as telephone numbers, home addresses, etc. It is a high risk of leakage the information if they are published. In this paper, we proposed a scene…

Accurately estimating the pose of an object is a crucial task in computer vision and robotics. There are two main deep learning approaches for this: geometric representation regression and iterative refinement. However, these methods have…

Semantic image editing requires inpainting pixels following a semantic map. It is a challenging task since this inpainting requires both harmony with the context and strict compliance with the semantic maps. The majority of the previous…

Context-aware translation can be achieved by processing a concatenation of consecutive sentences with the standard Transformer architecture. This paper investigates the intuitive idea of providing the model with explicit information about…

Ensemble weather predictions typically show systematic errors that have to be corrected via post-processing. Even state-of-the-art post-processing methods based on neural networks often solely rely on location-specific predictors that…

Intrinsic image decomposition aims to factorize an image into albedo (reflectance) and shading (illumination) sub-components. Being ill-posed and under-constrained, it is a very challenging computer vision problem. There are infinite pairs…

As the role played by statistical and computational sciences in climate and environmental modelling and prediction becomes more important, Machine Learning researchers are becoming more aware of the relevance of their work to help tackle…

Humans do not memorize everything. Thus, humans recognize scene changes by exploring the past images. However, available past (i.e., reference) images typically represent nearby viewpoints of the present (i.e., query) scene, rather than the…

Humans and animals show remarkable learning efficiency, adapting to new environments with minimal experience. This capability is not well captured by standard reinforcement learning algorithms that rely on incremental value updates. Rapid…

Removing adverse weather conditions like rain, fog, and snow from images is an important problem in many applications. Most methods proposed in the literature have been designed to deal with just removing one type of degradation. Recently,…

It is commonplace to encounter heterogeneous data, of which some aspects of the data distribution may vary but the underlying causal mechanisms remain constant. When data are divided into distinct environments according to the…

Recent work has shown how predictive modeling can endow agents with rich knowledge of their surroundings, improving their ability to act in complex environments. We propose question-answering as a general paradigm to decode and understand…

Neural architecture search methods are able to find high performance deep learning architectures with minimal effort from an expert. However, current systems focus on specific use-cases (e.g. convolutional image classifiers and recurrent…

Uniform and variable environments still remain a challenge for stable visual localization and mapping in mobile robot navigation. One of the possible approaches suitable for such environments is appearance-based teach-and-repeat navigation,…

We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch,…

Manipulating images of complex scenes to reconstruct, insert and/or remove specific object instances is a challenging task. Complex scenes contain multiple semantics and objects, which are frequently cluttered or ambiguous, thus hampering…