Meta tags:

Headings (most frequently used words):

results, color, editing, shape, abstract, video, method, transfer, real, image, applications, paper, acknowledgements,

Text of the page (most frequently used words):
the (40), shape (16), and (13), color (13), user (12), #editing (11), object (11), our (10), for (9), radiance (9), zhang (7), method (7), that (7), conditional (6), field (6), instances (6), edit (6), scribbles (6), views (5), instance (5), model (5), region (5), code (4), part (4), real (4), conduct (4), results (4), loss (4), category (4), network (4), this (3), can (3), fields (3), paper (3), single (3), novel (3), propagates (3), remove (3), across (3), over (3), optimize (3), reconstruction (3), scribble (3), nerf (3), introduce (3), components (3), was (2), adobe (2), research (2), richard (2), bibtex (2), liu (2), zhu (2), russell (2), image (2), transfer (2), between (2), codes (2), chair (2), unchanged (2), propagating (2), consistently (2), removal (2), both (2), density (2), based (2), regions (2), addition (2), sparse (2), foreground (2), change (2), background (2), prior (2), architecture (2), first (2), allowing (2), multiple (2), branch (2), which (2), learns (2), modular (2), during (2), video (2), neural (2), scene (2), coarse (2), propose (2), show (2), template, originally, made, eccv, project, found, work, while, intern, would, like, thank, william, freeman, helpful, discussions, here, colorful, phillip, isola, acknowledgements, hosted, arxiv, finetune, still, able, render, applications, simply, swapping, though, output, functionally, dependent, observe, changing, leaves, edits, add, encouraging, scribbled, selects, paste, into, similar, one, used, fill, rendering, provides, keep, encourage, but, maintain, propagate, learn, rich, plausible, looking, objects, training, several, builds, two, ways, each, represent, second, independent, generic, representation, due, design, only, few, need, modified, effectively, execute, supporting, high, quality, view, synthesis, optimized, per, explore, enabling, level, also, known, trained, specifically, space, modify, local, incorporates, new, including, shared, observing, same, underlying, semantics, without, any, supervision, thereby, propagation, entire, seat, next, hybrid, update, strategy, targets, specific, balances, efficiency, accuracy, interaction, formulate, optimization, problem, satisfies, constraints, preserves, original, structure, demonstrate, approach, various, tasks, three, datasets, outperforms, approaches, finally, appearance, photograph, extrapolated, abstract, demo, cmu, mit, csail, bryan, jun, yan, zhoutong, xiuming, steven, international, conference, computer, vision, iccv, 2021,

Text of the page (random words):
editing conditional radiance fields editing conditional radiance fields international conference on computer vision iccv 2021 steven liu 1 xiuming zhang 1 zhoutong zhang 1 richard zhang 2 jun yan zhu 3 bryan russell 2 1 mit csail 2 adobe research 3 cmu paper code video demo bibtex abstract a neural radiance field nerf is a scene model supporting high quality view synthesis optimized per scene in this paper we explore enabling user editing of a category level nerf also known as a conditional radiance field trained on a shape category specifically we introduce a method for propagating coarse 2d user scribbles to the 3d space to modify the color or shape of a local region first we propose a conditional radiance field that incorporates new modular network components including a shape branch that is shared across object instances observing multiple instances of the same category our model learns underlying part semantics without any supervision thereby allowing the propagation of coarse 2d user scribbles to the entire 3d region e g chair seat next we propose a hybrid network update strategy that targets specific network components which balances efficiency and accuracy during user interaction we formulate an optimization problem that both satisfies the user s constraints and preserves the original object structure we demonstrate our approach on various editing tasks over three shape datasets and show that it outperforms prior neural editing approaches finally we edit the appearance and shape of a real photograph and show that the edit propagates to extrapolated novel views video method to propagate sparse 2d user scribbles to novel views we learn a rich prior of plausible looking objects by training a single radiance field over several object instances our architecture builds on nerf in two ways first we introduce shape and color codes for each instance allowing a single radiance field to represent multiple object instances second we introduce an instance independent shape branch which learns a generic representation of the object category due to our modular architecture design only a few components of our network need to be modified during editing to effectively execute the user edit results color editing our method propagates sparse 2d user scribbles to fill an object region rendering the edit consistently across views the user provides a color a foreground scribble for the region to change and a background scribble for regions to keep unchanged to conduct the edit we optimize a reconstruction based loss to encourage the model to change the color at the foreground scribble but maintain the color on the background scribbles results shape editing our method propagates 2d user edits to remove or add an object part propagating the 2d edit consistently across views for shape removal the user scribbles over a region of the object to remove to conduct the removal we optimize both a reconstruction loss and a density based loss encouraging the model to remove density at the scribbled regions for shape addition the user selects an object part to paste into the instance to conduct the addition we optimize a reconstruction loss similar to the one used for color editing results color shape transfer our method can transfer shape and color between object instances simply by swapping the color and shape codes between instances though the color output of the model is functionally dependent on the shape code we observe that changing the shape code leaves the color of the chair unchanged results real image applications our method can finetune a conditional radiance field to a single still real image our method is able to render novel views of the real object instance and conduct color and shape editing on the instance paper s liu x zhang z zhang r zhang j y zhu b russell editing conditional radiance fields hosted on arxiv bibtex acknowledgements this template was originally made by phillip isola and richard zhang for a colorful eccv project the code can be found here part of this work while sl was an intern at adobe research we would like to thank william t freeman for helpful discussions