Wei Yang (杨卫)

Associate Professor
School of Computer Science & Technology, HUST
Room 306, Southern Building #6

I am an Associate Professor at the School of Computer Science, Huazhong University of Science and Technology, where I co-lead the HUST Media Lab. My research interests primarily lie in the areas of imaging, graphics, computer vision, and artificial intelligence.

Before joining HUST, I worked in the Advanced Technology and Projects (ATAP) division at Google in Mountain View, USA. As a proud member of the Te'veren team, I collaborated with Rick Marks on advanced sensing and on-device intelligence using computer vision. Prior to Google, I served as a Principal Scientist at DGene, US, where I conducted research on real-time volumetric human capture systems.

I graduated from the University of Delaware in 2017, where I majored in Computer Science. At UDel, I worked with Professor Jingyi Yu on research problems in computational photography and scene understanding. During my PhD, I interned at Adobe, hosted by the ACR team, in 2015.

I am actively seeking creative and highly motivated MS and PhD students who are passionate about research.

Email  /  Google Scholar  

• Area Chair: NeurIPS 23, CVPR 23, CVPR 24

• Program Committee: AAAI 20, AAAI 21, WACV 21, BMVC 18

• Reviewer: CVPR, ICCV, NeurIPS, ICML, ICLR, ECCV, TPAMI, TIP, TVCG...

* denotes equal contribution or co-corresponding author

We propose the Adaptable Motion Diffusion (AMD) model, which leverages a Large Language Model (LLM) to parse the input text into a sequence of concise and interpretable anatomical scripts that correspond to the target motion.

We propose to harness the capabilities of a Large Language Model (LLM) to decompose text descriptions into coherent directives adhering to stringent formats and progressively generate the target image.

We present a label-free white-box attack approach for ViT-based models that exhibits strong transferability to various black-box models by accelerating the feature collapse.

We propose a Feature Pruning and Consolidation (FPC) framework to circumvent explicit human structure parse, which consists of a sparse encoder, a global and local feature ranking module, and a feature consolidation decoder.

We formulates object detection and association jointly as a consistent denoising diffusion process from paired noise boxes to paired ground-truth boxes.

We propose to conduct inverse volume rendering by representing a scene using microflake volume, which assumes the space is filled with infinite small flakes and light reflects or scattersat each spatial location according to microflake distributions.

We propose to construct per-view cost frustum and fuse cross-view frustums for finer geometry estimation.

DreamFace is a progressive scheme to generate personalized 3D faces under text guidance.

We introduce HACK (Head-And-neCK), a novel parametric model for constructing the head and cervical region of digital humans.

We transplant the spirit of deformable convolution into the PatchMatch-based method for both memory-friendly and textureless-resilient MVS.

We demonstrate the basic vision transformer (ViT) architecture is sufficient for visual tracking with correlative masked modeling for information aggregation enhancement.

We propose an Uncertainty Regulated Dual Memory Units (UR-DMU) model to learn both the representations of normal data and discriminative features of abnormal data.

We present a neural representation with efficient generalization ability for high-fidelity free-view synthesis of dynamic humans.

CSWinTT is a new transformer architecture with multi-scale cyclic shifting window attention for visual object tracking, elevating the attention from pixel to window level.

ARTEMIS, the core of which is a neural-generated (NGI) animal engine, enables interactive motion control, real-time animation and photo-realistic rendering of furry animals.

NeuVV introduces a hyper-spherical harmonics (HH) decomposition for modeling smooth color variations over space and time.

We propose the AGG-CVCNet to learn complete geometry inference from partial observations with high confidence.

We present a learning-based, video-driven approach for generating dynamic facial geometries with high-quality physically-based assets

TightCap is a data-driven scheme to capture both the human shape and dressed garments accurately with only a single 3D human scan.

SportsCap -- the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input

We present a structure-from-motion (SfM) framework based on a special type of multi-perspective camera called the cross-slit or XSlit camera.

We generate a global full-body template by registering all poses in the acquired motion sequence, and then construct a deformable graph by utilizing the rigid components in the global template.

We use the light field (LF) camera such as Lytro and Raytrix as a virtual 3D scanner.

We present a comprehensive theory on ray geometry transforms under light field pose variations, and derive the transforms of three typical ray manifolds.

We present the depth dependent aspecratio (DDAR) property that can be used to 3D recovery.

We present a novel computational imaging solution for recovering AO by adopting a compressive sensing framework.

We explore coded aperture solutions on a special non-centric lens called the crossedslit (XSlit) lens.

We address the problem of determining CCP existence in general non-centric cameras.

I borrowed this website template from Jon Barron, thanks!