Related papers: InSituNet: Deep Image Synthesis for Parameter Spac…

Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is…

While recent advancements in multimodal language models have enabled image generation from expressive multi-image instructions, existing methods struggle to maintain performance under complex interleaved instructions. This limitation stems…

Implicit neural representation has demonstrated promising results in 3D reconstruction on various scenes. However, existing approaches either struggle to model fast-moving objects or are incapable of handling large-scale camera ego-motions…

We present three multi-scale similarity learning architectures, or DeepSim networks. These models learn pixel-level matching with a contrastive loss and are agnostic to the geometry of the considered scene. We establish a middle ground…

In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames. This objective encounters two main challenges: detecting all the dynamic…

Deep learning models have achieved significant success in various image related tasks. However, they often encounter challenges related to computational complexity and overfitting. In this paper, we propose an efficient approach that…

Today, more and more, it is necessary that most applications and documents developed in previous or current technologies to be accessible online on cloud-based infrastructures. That is why the migration of legacy systems including their…

Semantic Scene Completion aims at reconstructing a complete 3D scene with precise voxel-wise semantics from a single-view depth or RGBD image. It is a crucial but challenging problem for indoor scene understanding. In this work, we present…

Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…

Even though Deep Neural Networks are extremely powerful for image restoration tasks, they have several limitations. They are poorly understood and suffer from strong biases inherited from the training sets. One way to address these…

Deep learning approaches have become the standard solution to many problems in computer vision and robotics, but obtaining sufficient training data in high enough quality is challenging, as human labor is error prone, time consuming, and…

The ability for computational agents to reason about the high-level content of real world scene images is important for many applications. Existing attempts at addressing the problem of complex scene understanding lack representational…

Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep ensembles often come with high computational costs and memory…

Simulations of crystal growth are performed by using Convolutional Recurrent Neural Network surrogate models, trained on a dataset of time sequences computed by numerical integration of Allen-Cahn dynamics including faceting via kinetic…

The embedded ensemble propagation approach introduced in [49] has been demonstrated to be a powerful means of reducing the computational cost of sampling-based uncertainty quantification methods, particularly on emerging computational…

Particle settling in inclined channels is an important phenomenon that occurs during hydraulic fracturing of shale gas production. Generally, in order to accurately simulate the large-scale (field-scale) proppant transport process,…

Human can infer the 3D geometry of a scene from a sketch instead of a realistic image, which indicates that the spatial structure plays a fundamental role in understanding the depth of scenes. We are the first to explore the learning of a…

Recent studies shows that the majority of existing deep steganalysis models have a large amount of redundancy, which leads to a huge waste of storage and computing resources. The existing model compression method cannot flexibly compress…

Video-based representations have gained prominence in planning and decision-making due to their ability to encode rich spatiotemporal dynamics and geometric relationships. These representations enable flexible and generalizable solutions…

We propose ImGeoNet, a multi-view image-based 3D object detection framework that models a 3D space by an image-induced geometry-aware voxel representation. Unlike previous methods which aggregate 2D features into 3D voxels without…