Tianheng Cheng

8

Papers

113

Total Citations

Papers (8)

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding

MobileInst: Video Instance Segmentation on the Mobile

Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation

CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation

GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

YOLO-World: Real-Time Open-Vocabulary Object Detection

Symphonize 3D Semantic Scene Completion with Contextual Instance Queries