Chenhui Liu

Papers

Total Citations

H-Index

About

Chenhui Liu is a researcher whose work lies at the intersection of computer vision, spatial reasoning, and 3D understanding. His key research areas include developing datasets and models that enable machines to interpret and reason about three-dimensional structures from two-dimensional representations. Liu’s most notable contribution is the creation of SPARE3D, a pioneering dataset designed to benchmark spatial reasoning on three-view line drawings. This work, published in 2020 and garnering 18 citations, addresses a fundamental challenge: can deep networks replicate the human ability to infer 3D shapes and spatial relations from simple 2D line drawings? By curating this dataset, Liu has provided a critical resource for advancing research in geometric reasoning, pushing the boundaries of how artificial intelligence mimics human visual intelligence. His work is particularly impactful for students and researchers exploring the intersection of cognitive science and deep learning, offering a concrete tool to test and improve models’ spatial comprehension. Liu’s contributions highlight the ongoing quest to bridge the gap between human and machine understanding of the physical world.