81 citations · 180 across the 8 of their papers we have counts for
8 papers · 1 filter
Modality Forcing for Scalable Spatial Generation
Bardienus Pieter Duisterhof, Deva Ramanan, Jeffrey Ichnowski +2
Text-to-image (T2I) models contain rich spatial priors. Synthesizing photorealistic, cluttered scenes requires an understanding of geometry, including perspective and relative scal…
IllumiNeRF: 3D Relighting Without Inverse Rendering
Xiaoming Zhao, Pratul P. Srinivasan, Dor Verbin +3
Existing methods for relightable view synthesis -- using a set of images of an object under unknown lighting to recover a 3D representation that can be rendered from novel viewpoin…
ReconFusion: 3D Reconstruction with Diffusion Priors
Rundi Wu, Ben Mildenhall, Philipp Henzler +8
3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes. However, recovering a high-quality NeRF typically…
CamP: Camera Preconditioning for Neural Radiance Fields
Keunhong Park, Philipp Henzler, Ben Mildenhall +2
Neural Radiance Fields (NeRF) can be optimized to obtain high-fidelity 3D scene reconstructions of objects and large-scale scenes. However, NeRFs require accurate camera parameters…
HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields
Keunhong Park, Utkarsh Sinha, Peter Hedman +5
Neural Radiance Fields (NeRF) are able to reconstruct scenes with unprecedented fidelity, and various recent works have extended NeRF to handle dynamic scenes. A common approach to…
FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling
Christopher Xie, Keunhong Park, Ricardo Martin-Brualla +1
We investigate the use of Neural Radiance Fields (NeRF) to learn high quality 3D object category models from collections of input images. In contrast to previous work, we are able…
Nerfies: Deformable Neural Radiance Fields
Keunhong Park, Utkarsh Sinha, Jonathan T. Barron +4
We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones. Our approach augments neural ra…
LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation
Keunhong Park, Arsalan Mousavian, Yu Xiang +1
Current 6D object pose estimation methods usually require a 3D model for each object. These methods also require additional training in order to incorporate new objects. As a resul…