Shaohui Liu

Contact: "b1ueber2y at gmail dot com"     [Curriculum Vitae]
I am currently a final-year undergraduate at . I was an academic guest in the led by Prof. at in Summer 2019. My research interests include computer vision, computer graphics and computational photography.

I visited the at and remotely worked with Prof. from 2018 to 2019. Before that, I worked in the advised by Prof. . Also, I have worked at with Dr. and Dr. and at with Dr. .

   Selected Projects



DIST: Rendering with Differentiable Sphere Tracing

Shaohui Liu, , , , ,

CVPR, 2020.         Most work was done at .


A new differentiable sphere tracing algorithm enables systems to efficiently render various 2D observations from deep implicit signed distance functions and effectively perform robust inverse geometric optimization over real-world images with great generalization capability.


Towards Better Generalization: Joint Depth-Pose Learning without PoseNet

, Shaohui Liu, ,

CVPR, 2020.


Instead of relying on a PoseNet-like architecture, explicitly solving relative pose from optical flow correspondence improves the performance and generalization of self-supervised joint depth-pose learning methods on multiple challenging scenarios.



RepPoints: Point Set Representation for Object Detection

*, Shaohui Liu*, , ,

ICCV, 2019.         Intern project at .


Using a set of representative points to connect stages for simultaneous semantically aligned feature extraction and flexible geometric 2D representation produces a brand new effective object recognition framework without the need of anchors and bounding boxes.




Normalized Diversification

Shaohui Liu*, *, ,

CVPR, 2019.        


A novel loss term computed over the normalized pairwise distance matrices of the latent vectors and the corresponding outputs enforces both active extrapolation and safer interpolation of the mapping, ameliorating the notorious mode collapse problem on various vision applications.


Project August: Efficient Face Tracking at More than 1k FPS on CPU

Major project developer at in 2017.


By caching, reusing and sharing intermediate features of a lightweight regression-based tracking model across frames we achieved extremely efficient face tracking and deployed the system onto real-world market products, as a preprocessing step for subsequent face analysis.

[Note] See the commented texts in the HTML source code to view all projects.