This paper proposes a hybrid radiance field representation for unbounded...
Solving partial differential equations (PDEs) has been a fundamental pro...
Causal discovery in time-series is a fundamental problem in the machine
...
The neural radiance field (NeRF) achieved remarkable success in modeling...
Causal discovery from time-series data has been a central task in machin...
Imaging and perception in photon-limited scenarios is necessary for vari...
Implicit neural representation (INR) can describe the target scenes with...
Massive collection and explosive growth of the huge amount of medical da...
Increasing the layer number of on-chip photonic neural networks (PNNs) i...
Under low-light environment, handheld photography suffers from severe ca...
Signal capture stands in the forefront to perceive and understand the
en...
Noninvasive optical imaging through dynamic scattering media has numerou...
Human volumetric capture is a long-standing topic in computer vision and...
We propose DeepMultiCap, a novel method for multi-person performance cap...
High quality imaging usually requires bulky and expensive lenses to
comp...
In this paper, a novel convolutional neural network (CNN)-based framewor...
Human pose transfer, which aims at transferring the appearance of a give...
We introduce VERTEX, an effective solution to recover 3D shape and intri...
Deep implicit functions (DIFs), as a kind of 3D shape representation, ar...
Application-specific optical processors have been considered disruptive
...
Modeling 3D humans accurately and robustly from a single image is very
c...
Multi-view stereopsis (MVS) tries to recover the 3D model from 2D images...
Snapshot compressive imaging (SCI) aims to capture the high-dimensional
...
We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset,...
Image recognition is an important topic in computer vision and image
pro...
We propose DeepHuman, a deep learning based framework for 3D human
recon...
This paper proposes a new method for live free-viewpoint human performan...
We present a method to combine markerless motion capture and dense pose
...
Snapshot compressive imaging (SCI) refers to compressive imaging systems...
We propose DoubleFusion, a new real-time system that combines volumetric...
Single-pixel imaging (SPI) is a novel technique capturing 2D images usin...
Aiming at automatic, convenient and non-instrusive motion capture, this ...
Fourier ptychographic microscopy (FPM) is a novel computational coherent...
Specular reflection exists widely in photography and causes the recorded...
Causal inference in cue combination is to decide whether the cues have a...
Coded aperture imaging systems have recently shown great success in
reco...
Optical coherence tomography (OCT) is an important interferometric diagn...