publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

* Equal contribution.

2026

  1. Fire3D.gif
    FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute
    Hongchi Xia, Tianhang Cheng, Wei-Chiu Ma, and 1 more author
    arXiv preprint arXiv:2609.08848, 2026

    TL;DR: Feed-forward interactive 3D scene reconstruction from unsegmented images or casual videos within a minute.

  2. IMU4D.gif
    IMU4D: 4D Human-Object Understanding from Wearable IMUs
    Hao-Yu Hsu*, Tianhang Cheng*, Jing Wen, and 2 more authors
    2026

    TL;DR: 4D human-object understanding from wearable IMUs.

2025

  1. plant.png
    Demeter: A Parametric Model of Crop Plant Morphology from the Real World
    Tianhang Cheng, Albert J. Zhai, Evan Z. Chen, and 13 more authors
    In IEEE/CVF International Conference on Computer Vision, 2025

    TL;DR: A 3D soybean dataset and the parametric model for crop plants

2024

  1. relight_dataset.png
    Objects with Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting
    Benjamin Ummenhofer, Sanskar Agrawal, Rene Sepulveda, and 6 more authors
    In International Conference on 3D Vision, 2024

    TL;DR: A real-world dataset for evaluating inverse rendering methods in object relighting, allowing for a comprehensive analysis of relighting performance.

2023

  1. dup.gif
    Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects
    Tianhang Cheng, Wei-Chiu Ma, Kaiyu Guan, and 2 more authors
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023

    TL;DR: Inverse rendering from a pile of similar objects.

2020

  1. cloak.png
    Designing conformal cloaks by manipulating structures directly in the physical space
    Zhanyi Wang, Yichao Liu, Tianhang Cheng, and 2 more authors
    Optics Express, 2020

    TL;DR: Design conformal cloaks by manipulating structures directly in the physical space