Skip to content
Avatar
:octocat:
Working from home
:octocat:
Working from home
weihaox/README.md

Hi there 👋

github stats

  • 🔭 My main research interests are computer vision, computer graphic, and human–computer interaction. The ultimate vision of my research is to manifest the physical world through imagination.

  • I am currently working on controllable, interpretable, and generalizable visual contents generation, especially generating 2D images, videos, or 3D shapes from multi-modal information (e.g., sketches, labels, or textual descriptions).

  • 🌱 I’m also concerned about the Data Bias and Efficiency and AI Robustness, Fairness, and Privacy in generation tasks.

  • 📫 Find my info at xiaweihao.com. Reach me through weihaox AT outlook.com.

Pinned

  1. A collection of awesome resources image-to-image translation.

    371 57

  2. A collection of resources on neural rendering.

    452 48

  3. Pytorch implementation for TediGAN: Text-Guided Diverse Image Generation and Manipulation.

    21 3

  4. A large-scale face image dataset that allows text-to-image-generation, text-guided image manipulation, sketch-to-image generation, and GANs for face generation and editing.

    14 4

  5. This is the UNOFFICIAL implementation of the ICCV 2019 paper 'Exploiting Temporal Consistency for Real-Time Video Depth Estimation'.

    Python 9 1

  6. Code and Data For Controllable Continuous Gaze Redirection.

    Jupyter Notebook 7 3

246 contributions in the last year

Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec Jan Mon Wed Fri

Contribution activity

Seeing something unexpected? Take a look at the GitHub profile guide.