I am a second-year master student at the University of Illinois at Urbana-Champaign, advised by Prof. James M. Rehg. Previously, I got my
Bachelor's degree in Computer Science from University of Illinois at Urbana-Champaign under the supervision of Prof.
Svetlana Lazebnik. My research interest lies in 3D/4D Reconstructions and 3D Generative Models.
We introduce Cue3D, the first comprehensive, model-agnostic framework for quantifying the influence of individual image cues in single-image 3D generation.
DenseScan: Advancing 3D Scene Understanding with 2D Dense Annotation Zirui Wang*,
Tao Zhang,
NeurIPS Workshop on Space in Vision, Language, and Embodied AI, 2025
[Paper]
We introduce DenseScan, a novel dataset with detailed multi-level descriptions generated by an automated pipeline leveraging multi-view 2D images and multimodal large language models (MLLMs).
We propose the Hierarchical Memory-Aware Transformer (HiMemFormer), a novel approach that simultaneously learns feature
representations from both contextual and agent-specified dimensions through a dual-hierarchical framework.