Yi-Hsuan Tsai

7

Papers

20

Total Citations

Papers (7)

Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splatting

Self-Training Room Layout via Geometry-aware Ray-casting

MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh

What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning

Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes

Text-Driven Image Editing via Learnable Regions

PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection