95 citations · 260 across the 15 of their papers we have counts for
15 papers
MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field
Kaizhi Yang, Xiaoshuai Zhang, Zhiao Huang +3
We present MovingParts, a NeRF-based method for dynamic scene reconstruction and part discovery. We consider motion as an important cue for identifying parts, that all particles on…
TensoIR: Tensorial Inverse Rendering
Haian Jin, Isabella Liu, Peijia Xu +6
We propose TensoIR, a novel inverse rendering approach based on tensor factorization and neural fields. Unlike previous works that use purely MLP-based neural fields, thus sufferin…
Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision
Xiaoshuai Zhang, Abhijit Kundu, Thomas Funkhouser +3
We address efficient and structure-aware 3D scene representation from images. Nerflets are our key contribution -- a set of local neural radiance fields that together represent a s…
NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction
Xiaoshuai Zhang, Sai Bi, Kalyan Sunkavalli +2
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-scale…
Close the Optical Sensing Domain Gap by Physics-Grounded Active Stereo Sensor Simulation
Xiaoshuai Zhang, Rui Chen, Ang Li +11
In this paper, we focus on the simulation of active stereovision depth sensors, which are popular in both academic and industry communities. Inspired by the underlying mechanism of…
ActiveZero: Mixed Domain Learning for Active Stereovision with Zero Annotation
Isabella Liu, Edward Yang, Jianyu Tao +5
Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground trut…
Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models
Jen-Hao Rick Chang, Ashish Shrivastava, Hema Swetha Koppula +2
Controllable generative sequence models with the capability to extract and replicate the style of specific examples enable many applications, including narrating audiobooks in diff…
MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
Anpei Chen, Zexiang Xu, Fuqiang Zhao +4
We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that…
Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance
Minghua Liu, Xiaoshuai Zhang, Hao Su
We are interested in reconstructing the mesh representation of object surfaces from point clouds. Surface reconstruction is a prerequisite for downstream applications such as rende…
Disentangled Image Matting
Shaofan Cai, Xiaoshuai Zhang, Haoqiang Fan +6
Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap.…
A Comprehensive Benchmark for Single Image Compression Artifacts Reduction
Jiaying Liu, Dong Liu, Wenhan Yang +3
We present a comprehensive study and evaluation of existing single image compression artifacts removal algorithms, using a new 4K resolution benchmark including diversified foregro…
How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning
Xinlei Pan, Weiyao Wang, Xiaoshuai Zhang +3
Machine learning has been widely applied to various applications, some of which involve training with privacy-sensitive data. A modest number of data breaches have been studied, in…
Bridging the Gap Between Computational Photography and Visual Recognition
Rosaura G. VidalMata, Sreya Banerjee, Brandon RichardWebster +21
What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algo…
DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal
Xiaoshuai Zhang, Wenhan Yang, Yueyu Hu +1
JPEG is one of the most commonly used standards among lossy image compression methods. However, JPEG compression inevitably introduces various kinds of artifacts, especially at hig…
Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration
Xiaoshuai Zhang, Yiping Lu, Jiaying Liu +1
In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels in one model. The proposed control…