Shaohui Liu

Contact: "b1ueber2y at gmail dot com"       [Curriculum Vitae]
I am currently a PhD student in the at advised by Prof. . I am mainly interested in 3D computer vision, multi-view geometry and its applications to real-world practice.

I obtained my bachelor's degree from Department of Electronic Engineering, . From 2018 to 2019, I visited the at and remotely worked with Prof. . After that, I had an academic visit at CVG and started as a Direct Doctorate student in Fall 2020. I have also spent time at , , and .

   Selected Projects

3D Line Mapping Revisited

Shaohui Liu, , , ,

CVPR, 2023.         Selected as a highlight paper.

An open-sourced system that robustly and efficiently constructs 3D line maps from multi-view imagery benefits multiple downstream applications such as visual localization and hybrid bundle adjustment, while also being flexible to adaptation of different 2D line detectors and matchers.

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras

, Shaohui Liu, , ,

ECCV, 2022.         Part of my intern project at .

Connecting, optimizing dense point trajectories from pairwise optical flows and segmenting them into labeled point tracks benefit an effective global structure-from-motion system for dynamic in-the-wild videos (image sequences) that exhibit complex foreground motions.

NerfingMVS: Guided Optimization of NeRF for Indoor Multi-view Stereo

, Shaohui Liu, , , ,

ICCV, 2021 / T-PAMI, 2023.         Accepted as an Oral.

Integrating conventional SfM + MVS reconstruction and learning-based depth priors largely improves the learned geometry of neural radiance fields (NeRF) in general indoor scenes, leading to significantly better multi-view depth estimation and novel view synthesis.

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.

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.