Related papers: Skyeyes: Ground Roaming using Aerial View Images
Generating explorable 3D scenes from a single image is a highly challenging problem in 3D vision. Existing methods struggle to support free exploration, often producing severe geometric distortions and noisy artifacts when the viewpoint…
Extensions of Neural Radiance Fields (NeRFs) to model dynamic scenes have enabled their near photo-realistic, free-viewpoint rendering. Although these methods have shown some potential in creating immersive experiences, two drawbacks limit…
We investigate whether video generative models can exhibit visuospatial intelligence, a capability central to human cognition, using only visual data. To this end, we present Video4Spatial, a framework showing that video diffusion models…
Capturing and faithfully rendering photo-realistic humans from novel views is a fundamental problem for AR/VR applications. While prior work has shown impressive performance capture results in laboratory settings, it is non-trivial to…
Aerial cinematography is significantly expanding the capabilities of film-makers. Recent progress in autonomous unmanned aerial vehicles (UAVs) has further increased the potential impact of aerial cameras, with systems that can safely track…
Data-driven algorithms have surpassed traditional techniques in almost every aspect in robotic vision problems. Such algorithms need vast amounts of quality data to be able to work properly after their training process. Gathering and…
Immersive maps such as Google Street View and Bing Streetside provide true-to-life views with a massive collection of panoramas. However, these panoramas are only available at sparse intervals along the path they are taken, resulting in…
This paper studies the task of SatStreet-view synthesis, which aims to render photorealistic street-view panorama images and videos given any satellite image and specified camera positions or trajectories. We formulate to learn neural…
In this work, we present a novel method for extensive multi-scale generative terrain modeling. At the core of our model is a cascade of superresolution diffusion models that can be combined to produce consistent images across multiple…
Predicting realistic ground views from satellite imagery in urban scenes is a challenging task due to the significant view gaps between satellite and ground-view images. We propose a novel pipeline to tackle this challenge, by generating…
We present a method for novel view synthesis from input images that are freely distributed around a scene. Our method does not rely on a regular arrangement of input views, can synthesize images for free camera movement through the scene,…
It is desirable to create 3D object models and 3D maps from 2D input images for applications such as navigation, virtual tourism, and urban planning. The traditional methods of creating 3D maps, (such as photogrammetry), require a large…
The emerging field of panoramic video generation from text and image prompts unlocks new creative possibilities in virtual reality (VR), addressing the limitations of current immersive experiences, which are constrained by pre-designed…
With the development of deep neural networks, the demand for a significant amount of annotated training data becomes the performance bottlenecks in many fields of research and applications. Image synthesis can generate annotated images…
Driving World Models (DWMs) have become essential for autonomous driving by enabling future scene prediction. However, existing DWMs are limited to scene generation and fail to incorporate scene understanding, which involves interpreting…
Recent advancements in 3D Gaussian Splatting (3D-GS) have demonstrated the potential of using 3D Gaussian primitives for high-speed, high-fidelity, and cost-efficient novel view synthesis from continuously calibrated input views. However,…
Visual context is important in object recognition and it is still an open problem in computer vision. Along with the advent of deep convolutional neural networks (CNN), using contextual information with such systems starts to receive…
Large-scale scene data is essential for training and testing in robot learning. Neural reconstruction methods have promised the capability of reconstructing large physically-grounded outdoor scenes from captured sensor data. However, these…
Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing all occluded surfaces. While much progress has been made on…
We propose a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images without…