Research in computer vision & robotics

Fei Teng 滕飞

Ph.D. Candidate Hunan University

Omnidirectional Scene Understanding
& Controllable Generation

To address perception bottlenecks faced by robots and autonomous vehicles in complex real-world environments, my research centers on fine-grained visual modeling and understanding of the physical world. I investigate physically grounded geometric and semantic scene representations, as well as controllable generative modeling and learning from synthetic data, with an emphasis on omnidirectional observations.

Portrait of Fei Teng

Research Focus

3D + Visual connected with Generation & Learning

First- or co-first-authored / total

(1/5)

3D Scene Understanding

Geometric and semantic scene representations from omnidirectional observations, including 3D occupancy prediction and BEV semantic mapping.

(4/4)

Controllable Generation & Synthetic Data Learning

Scene- and motion-conditioned image and video generation, alongside effective learning from synthetic data.

(4/10)

Visual Understanding & Reasoning

Fine-grained visual understanding across images and videos, spanning scene parsing, object tracking, and multimodal reasoning.

Omnidirectional Sensing Platforms

Custom-integrated sensing systems for real-world data collection and perception benchmarking.

Autonomous driving & quadruped robotics

Autonomous Driving

A vehicle-mounted system integrating spherical imaging and LiDAR, built to support the Spheriverse dataset and its 3D perception benchmarks.

Quadruped Robotics

A quadruped-mounted system integrating panoramic RGB, thermal, polarization, and LiDAR sensing for the PanoMMOcc dataset and multimodal occupancy benchmark.

Representative Works

All publications

Publications & papers under review

Research Archive 19

Google Scholar

In Preparation

xxx1In preparation
xxx2In preparation
xxx3In preparation

A little background

Education & Research

I am a Ph.D. candidate at Hunan University, advised by Prof. Kailun Yang. I received my M.Eng. from the Karlsruhe Institute of Technology (KIT) and my B.Eng. from China University of Mining and Technology in Xuzhou.

Contact

Let's connect.

Research conversations and collaborations are welcome.

feiteng@hnu.edu.cn