no code implementations • 21 Nov 2023 • Andrew Spielberg, Fangcheng Zhong, Konstantinos Rematas, Krishna Murthy Jatavallabhula, Cengiz Oztireli, Tzu-Mao Li, Derek Nowrouzezahrai
This approach is predicated by neural network differentiability, the requirement that analytic derivatives of a given problem's task metric can be computed with respect to neural network's parameters.
no code implementations • 20 Nov 2023 • Chenliang Zhou, Fangcheng Zhong, Param Hanji, Zhilin Guo, Kyle Fogarty, Alejandro Sztrajman, Hongyun Gao, Cengiz Oztireli
We propose FrePolad: frequency-rectified point latent diffusion, a point cloud generation pipeline integrating a variational autoencoder (VAE) with a denoising diffusion probabilistic model (DDPM) for the latent distribution.
no code implementations • 23 Aug 2023 • Wenzhao Li, Tianhao Wu, Fangcheng Zhong, Cengiz Oztireli
We highlight a research gap in radiance fields style transfer, the lack of sufficient perceptual controllability, motivated by the existing concept in the 2D image style transfer.
no code implementations • 17 Mar 2023 • Tianhao Wu, Hanxue Liang, Fangcheng Zhong, Gernot Riegler, Shimon Vainer, Cengiz Oztireli
While neural radiance field (NeRF) based methods can model semi-transparency and achieve photo-realistic quality in synthesized novel views, their volumetric geometry representation tightly couples geometry and opacity, and therefore cannot be easily converted into surfaces without introducing artifacts.
no code implementations • 8 Oct 2022 • Chenliang Zhou, Fangcheng Zhong, Cengiz Oztireli
We introduce CLIP Projection-Augmentation Embedding (PAE) as an optimization target to improve the performance of text-guided image manipulation.
no code implementations • 31 May 2022 • Tianhao Wu, Fangcheng Zhong, Andrea Tagliasacchi, Forrester Cole, Cengiz Oztireli
We introduce Decoupled Dynamic Neural Radiance Field (D$^2$NeRF), a self-supervised approach that takes a monocular video and learns a 3D scene representation which decouples moving objects, including their shadows, from the static background.
1 code implementation • CVPR 2022 • Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J. Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti, Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi
Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details.
1 code implementation • 16 Sep 2020 • Param Hanji, Fangcheng Zhong, Rafal K. Mantiuk
A near-optimal reconstruction of the radiance of a High Dynamic Range scene from an exposure stack can be obtained by modeling the camera noise distribution.