no code implementations • 9 Oct 2023 • Ruiyang Liu, Jinxu Xiang, Bowen Zhao, Ran Zhang, Jingyi Yu, Changxi Zheng
To tackle the problem of efficiently editing neural implicit fields, we introduce Neural Impostor, a hybrid representation incorporating an explicit tetrahedral mesh alongside a multigrid implicit field designated for each tetrahedron within the explicit mesh.
no code implementations • 25 Aug 2023 • Xinyuan Li, Yu Ji, Yanchen Liu, Xiaochen Hu, Jinwei Ye, Changxi Zheng
Leveraging the markers, we design a multi-camera system that captures surface deformation under the UV light and the visible light in a time multiplexing fashion.
1 code implementation • 24 May 2023 • Rundi Wu, Ruoshi Liu, Carl Vondrick, Changxi Zheng
Specifically, we encode the input 3D textured shape into triplane feature maps that represent the signed distance and texture fields of the input.
no code implementations • 30 Sep 2022 • Honglin Chen, Rundi Wu, Eitan Grinspun, Changxi Zheng, Peter Yichen Chen
Whereas classical solvers can dynamically adapt their spatial representation only by resorting to complex remeshing algorithms, our INSR approach is intrinsically adaptive.
no code implementations • 5 Aug 2022 • Rundi Wu, Changxi Zheng
Existing generative models for 3D shapes are typically trained on a large 3D dataset, often of a specific object category.
no code implementations • 15 Sep 2021 • Henrique Teles Maia, Chang Xiao, DIngzeyu Li, Eitan Grinspun, Changxi Zheng
We find that each layer component's evaluation produces an identifiable magnetic signal signature, from which layer topology, width, function type, and sequence order can be inferred using a suitably trained classifier and a joint consistency optimization based on integer programming.
1 code implementation • ICCV 2021 • Rundi Wu, Chang Xiao, Changxi Zheng
We present the first 3D generative model for a drastically different shape representation --- describing a shape as a sequence of computer-aided design (CAD) operations.
1 code implementation • CVPR 2021 • Jianjin Xu, Changxi Zheng
Given a trained GAN and as few as eight semantic annotations, the user is able to generate diverse images subject to a user-provided semantic layout, and control the synthesized image semantics.
1 code implementation • NeurIPS 2020 • Ruilin Xu, Rundi Wu, Yuko Ishiwaka, Carl Vondrick, Changxi Zheng
We introduce a deep learning model for speech denoising, a long-standing challenge in audio analysis arising in numerous applications.
1 code implementation • CVPR 2020 • Chang Xiao, Changxi Zheng
To defend against adversarial examples, a plausible idea is to obfuscate the network's gradient with respect to the input image.
1 code implementation • ICLR 2020 • Chang Xiao, Peilin Zhong, Changxi Zheng
In all cases, the robustness of k-WTA networks outperforms that of traditional networks under white-box attacks.
no code implementations • NeurIPS 2019 • Peilin Zhong, Yuchen Mo, Chang Xiao, Peng-Yu Chen, Changxi Zheng
The conventional wisdom to this end is by reducing through training a statistical distance (such as $f$-divergence) between the generated distribution and provided data distribution.
1 code implementation • NeurIPS 2018 • Chang Xiao, Peilin Zhong, Changxi Zheng
This paper addresses the mode collapse for generative adversarial networks (GANs).
no code implementations • 12 May 2018 • Dingzeyu Li, Timothy R. Langlois, Changxi Zheng
In our validations, we show that our synthesized spatial audio matches closely with recordings using ambisonic microphones.
no code implementations • 28 Jul 2017 • Chang Xiao, Cheng Zhang, Changxi Zheng
We then introduce an algorithm that embeds a user-provided message in the text document and produces an encoded document whose appearance is minimally perturbed from the original document.
no code implementations • 18 Jul 2017 • Dingzeyu Li, Avinash S. Nair, Shree K. Nayar, Changxi Zheng
We present AirCode, a technique that allows the user to tag physically fabricated objects with given information.