I'm Tianheng Cheng, pursuing my Ph.D. now and working on Computer Vision and Machine Intelligence.

My research goal is to enable machines/robots to see and understand the world.

Previous works/publications are listed at Google Scholar 📚.

Currently, I'm devoted to research on large multimodal models, foundational visual-language modeling, and image generation. Before that, I mainly focused on fundamental tasks such as object detection and instance segmentation, as well as visual perception for autonomous driving.

Highlighted Works of those pinned works:

• The latest works 🔥: EVF-SAM (arXiv) empowers segment-anything (SAM, SAM-2) with the strong text-prompting ability. Try our demo on HuggingFace.
• OSP (ECCV 2024) explores sparse set of points to predict 3D semantic occupancy for autonomous vehicles, which is a brand new formulation!
• YOLO-World (CVPR 2024) for real-time open-vocabulary object detection; Symphonies (CVPR 2024) for camera-based 3D scene completion.
• SparseInst (CVPR 2022) aims for real-time instance segmentation with a simple fully convolutional framework! MobileInst (AAAI 2024) further explores temporal consistency and kernel reuse for efficient mobile video instance segmentation.
• BoxTeacher (CVPR 2023) bridges the gap between fully supervised and box-supervised instance segmentation. With ~1/10 annotation cost, BoxTeacher can achieve 93% performance versus fully supervised methods.
• BMask R-CNN (ECCV 2020) is the first work to introduce boundary modeling for objects and aims for high-performance instance segmentation. It leads the research about object boundaries for instance segmentation.
• GKT (arXiv) addresses the ill-posed 2D-to-3D (Surrounding views to Bird-Eye views) transformation with the concern about accuracy and speed, especially for practical implementation for autonomous systems.