Nerfusion: Fusing radiance fields for large-scale scene reconstruction

X Zhang, S Bi, K Sunkavalli, H Su… - Proceedings of the …, 2022 - openaccess.thecvf.com
While NeRF has shown great success for neural reconstruction and rendering, its limited
MLP capacity and long per-scene optimization times make it challenging to model large …

Neural point-based graphics

KA Aliev, A Sevastopolsky, M Kolos, D Ulyanov… - Computer Vision–ECCV …, 2020 - Springer
We present a new point-based approach for modeling the appearance of real scenes. The
approach uses a raw point cloud as the geometric representation of a scene, and augments …

Texturedreamer: Image-guided texture synthesis through geometry-aware diffusion

YY Yeh, JB Huang, C Kim, L **_for_Volumetric_Neural_Rendering_CVPR_2021_paper.pdf" data-clk="hl=sk&sa=T&oi=gga&ct=gga&cd=4&d=6083521862060994562&ei=HEe9Z_nuOZ-bieoPq73r0Qw" data-clk-atid="AvB30-YCbVQJ" target="_blank">[PDF] thecvf.com

Neutex: Neural texture map** for volumetric neural rendering

F **ang, Z Xu, M Hasan… - Proceedings of the …, 2021 - openaccess.thecvf.com
Recent work has demonstrated that volumetric scene representations combined with
differentiable volume rendering can enable photo-realistic rendering for challenging scenes …

Stylemesh: Style transfer for indoor 3d scene reconstructions

L Höllein, J Johnson, M Nießner - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
We apply style transfer on mesh reconstructions of indoor scenes. This enables VR
applications like experiencing 3D environments painted in the style of a favorite artist. Style …

Deep reflectance volumes: Relightable reconstructions from multi-view photometric images

S Bi, Z Xu, K Sunkavalli, M Hašan… - Computer Vision–ECCV …, 2020 - Springer
We present a deep learning approach to reconstruct scene appearance from unstructured
images captured under collocated point lighting. At the heart of Deep Reflectance Volumes …

360-degree textures of people in clothing from a single image

V Lazova, E Insafutdinov… - … Conference on 3D Vision …, 2019 - ieeexplore.ieee.org
In this paper we predict a full 3D avatar of a person from a single image. We infer texture and
geometry in the UV-space of the SMPL model using an image-to-image translation method …

Deep view synthesis from sparse photometric images

Z Xu, S Bi, K Sunkavalli, S Hadap, H Su… - ACM Transactions on …, 2019 - dl.acm.org
The goal of light transport acquisition is to take images from a sparse set of lighting and
viewing directions, and combine them to enable arbitrary relighting with changing view …

Ref-npr: Reference-based non-photorealistic radiance fields for controllable scene stylization

Y Zhang, Z He, J **ng, X Yao… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Current 3D scene stylization methods transfer textures and colors as styles using arbitrary
style references, lacking meaningful semantic correspondences. We introduce Reference …