Meta tags:

Headings (most frequently used words):

urban, radiance, fields, abstract, video, novel, view, synthesis, mesh, reconstruction, citation, cvpr, 2022,

Text of the page (most frequently used words):
and (15), the (8), for (6), novel (6), view (4), images (4), video (3), urban (3), #radiance (3), fields (3), our (3), data (3), captured (3), world (2), mesh (2), use (2), three (2), konstantinos (2), rematas (2), andrew (2), liu (2), pratul (2), srinivasan (2), jonathan (2), barron (2), andrea (2), tagliasacchi (2), tom (2), funkhouser (2), vittorio (2), ferrari (2), cvpr (2), 2022 (2), visualize (2), load (2), reconstruction (2), synthesis (2), from (2), outdoor (2), street (2), rgb (2), lidar (2), which (2), can (2), neural (2), methods (2), leveraging (2), was, made, authors, using, blender, adobe, premiere, pro, interactive, map, based, visualization, article, rematas2022urf, title, author, journal, year, citation, method, extract, colored, meshes, them, browser, may, take, some, time, click, city, camera, trajectory, wait, bit, goal, this, work, perform, scanning, platforms, commonly, deployed, mapping, environments, given, sequence, posed, sweeps, acquired, cameras, scanners, moving, through, scene, produce, model, surfaces, extracted, synthesized, approach, extends, has, been, demonstrated, synthesize, realistic, small, scenes, controlled, settings, with, new, asynchronously, addressing, exposure, variation, between, predicted, image, segmentations, supervise, densities, rays, pointing, sky, each, these, extensions, provides, significant, performance, improvements, experiments, system, produces, state, art, surface, reconstructions, synthesizes, higher, quality, views, comparison, both, traditional, colmap, recent, representations, mip, nerf, abstract, arxiv, paper, urf,

Text of the page (random words):
urf urban radiance fields konstantinos rematas andrew liu pratul p srinivasan jonathan t barron andrea tagliasacchi tom funkhouser vittorio ferrari cvpr 2022 paper arxiv video abstract the goal of this work is to perform 3d reconstruction and novel view synthesis from data captured by scanning platforms commonly deployed for world mapping in urban outdoor environments e g street view given a sequence of posed rgb images and lidar sweeps acquired by cameras and scanners moving through an outdoor scene we produce a model from which 3d surfaces can be extracted and novel rgb images can be synthesized our approach extends neural radiance fields which has been demonstrated to synthesize realistic novel images for small scenes in controlled settings with new methods for leveraging asynchronously captured lidar data for addressing exposure variation between captured images and for leveraging predicted image segmentations to supervise densities on rays pointing at the sky each of these three extensions provides significant performance improvements in experiments on street view data our system produces state of the art 3d surface reconstructions and synthesizes higher quality novel views in comparison to both traditional methods e g colmap and recent neural representations e g mip nerf video novel view synthesis click on a city to visualize a novel camera trajectory wait a bit to load mesh reconstruction we use our method to extract colored meshes and visualize them on the browser it may take some time to load citation article rematas2022urf title urban radiance fields author konstantinos rematas and andrew liu and pratul p srinivasan and jonathan t barron and andrea tagliasacchi and tom funkhouser and vittorio ferrari journal cvpr year 2022 the video was made by the authors using blender and adobe premiere pro the interactive world map is based on d3 js for the mesh visualization we use three js