Related papers: Equivariant Light Field Convolution and Transforme…

We integrate two powerful ideas, geometry and deep visual representation learning, into recurrent network architectures for mobile visual scene understanding. The proposed networks learn to "lift" and integrate 2D visual features over time…

This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception…

Light field cameras have been proved to be powerful tools for 3D reconstruction and virtual reality applications. However, the limited resolution of light field images brings a lot of difficulties for further information display and…

Scanpath prediction in 360{\deg} images can help realize rapid rendering and better user interaction in Virtual/Augmented Reality applications. However, existing scanpath prediction models for 360{\deg} images execute scanpath prediction on…

In this work, we propose a 3D fully convolutional architecture for video saliency prediction that employs hierarchical supervision on intermediate maps (referred to as conspicuity maps) generated using features extracted at different…

Feed-forward 3D reconstruction models such as DUSt3R, VGGT, and Depth Anything 3 (DA3) are transformer-based foundation models that infer camera geometry and dense scene structure in a single forward pass. Trained at scale in a supervised…

Feed-forward foundation models for multi-view 3-dimensional (3D) reconstruction have been trained on large-scale datasets of perspective images; when tested on wide field-of-view images, e.g., from a fisheye camera, their performance…

3D object detection from a single image without LiDAR is a challenging task due to the lack of accurate depth information. Conventional 2D convolutions are unsuitable for this task because they fail to capture local object and its scale…

Spatial understanding of the semantics of the surroundings is a key capability needed by autonomous cars to enable safe driving decisions. Recently, purely vision-based solutions have gained increasing research interest. In particular,…

Recently, 3D face reconstruction and face alignment tasks are gradually combined into one task: 3D dense face alignment. Its goal is to reconstruct the 3D geometric structure of face with pose information. In this paper, we propose a graph…

Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and view synthesis. Despite achieving high-quality results for common benchmarks with curated data, outputs often degrade for data that…

We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances. Most approaches for multiview shape reconstruction operate on sparse shape…

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…

In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry, camera parameters, and a neural renderer that approximates…

We suggest a method to directly deep-learn light transport, i. e., the mapping from a 3D geometry-illumination-material configuration to a shaded 2D image. While many previous learning methods have employed 2D convolutional neural networks…

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs…

We propose a general architecture that combines the coefficient learning scheme with a residual operator layer for learning mappings between continuous functions in the 3D Euclidean space. Our proposed model is guaranteed to achieve…

In this work, we propose a step towards a more accurate prediction of the environment light given a single picture of a known object. To achieve this, we developed a deep learning method that is able to encode the latent space of indoor…

Recent illumination estimation methods have focused on enhancing the resolution and improving the quality and diversity of the generated textures. However, few have explored tailoring the neural network architecture to the Equirectangular…

We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations. Our method capitalizes on moving characters being equivariant with respect…