Jiahao Ma

Hello, I'm Jiahao Ma

I am a second-year PhD student in Computer Science at Australian National University where I am advised by Miaomiao Liu, David Ahmedt Aristizabal and Chuong Nguyen. Before that, I received my Master of Philosophy degree supervised by Liang Zheng from Australian National University in 2023. My current research interest lies in 3D reconstruction and novel view synthesis.


Publications

SOAF: Scene Occlusion-aware Neural Acoustic Field

SOAF: Scene Occlusion-aware Neural Acoustic Field

Arxiv preprint

SOAF models room geometry and wall occlusions for sound propagation.

HashPoint: Accelerated Point Searching and Sampling for Neural Rendering

HashPoint: Accelerated Point Searching and Sampling for Neural Rendering

CVPR, 2024 Highlight

HashPoint accelerates the volume rendering by combining rasterization with ray tracing.

Multiview Detection with Cardboard Human Modeling

Multiview Detection with Cardboard Human Modeling

ACCV, 2024

Cardboard human modeling aggregate multiview pedestrian features.

Voxelized 3D Feature Aggregation for Multiview Detection

Voxelized 3D Feature Aggregation for Multiview Detection

DICTA, 2024

VFA, a voxelized 3D feature aggregation method, improves multiview detection accuracy by reducing occlusion and projection errors.

* denotes equal contribution.

Projects

MultiviewC GIF

Multiview animal monitoring

Multiview detection algorithm design and synthetic dataset generation.

  • Publication: The paper has been accepted by DICTA 2024.
  • MultiviewC dataset: Proposed the MultiviewC dataset for multiview animal action recognition, 3D detection, and tracking.