papers

Publications (8)

cs.CV2025

Tracking-Guided 4D Generation: Foundation-Tracker Motion Priors for 3D Model Animation

Su Sun, Cheng Zhao, Himangi Mittal +4

Generating dynamic 4D objects from sparse inputs is difficult because it demands joint preservation of appearance and motion coherence across views and time while suppressing artif…

cs.CV2024

TCLC-GS: Tightly Coupled LiDAR-Camera Gaussian Splatting for Autonomous Driving

Cheng Zhao, Su Sun, Ruoyu Wang +6

Most 3D Gaussian Splatting (3D-GS) based methods for urban scenes initialize 3D Gaussians directly with 3D LiDAR points, which not only underutilizes LiDAR data capabilities but al…

cs.CV2024

Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion

Su Sun, Cheng Zhao, Yuliang Guo +4

In this paper, we present a novel indoor 3D reconstruction method with occluded surface completion, given a sequence of depth readings. Prior state-of-the-art (SOTA) methods only f…

cs.CV2026

Smartphone-based Circular Plot Sampling for Forest Inventory

Su Sun, Jui-Cheng Chiu, Nabin Khanal +2

Circular sample plots are a cornerstone of forest inventory, yet accurate measurement of tree diameter at breast height (DBH) and spatial location within such plots remains challen…

cs.CV2025

SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Driving

Su Sun, Cheng Zhao, Zhuoyang Sun +2

Most existing Dynamic Gaussian Splatting methods for complex dynamic urban scenarios rely on accurate object-level supervision from expensive manual labeling, limiting their scalab…

cs.GR2024

M2fNet: Multi-modal Forest Monitoring Network on Large-scale Virtual Dataset

Yawen Lu, Yunhan Huang, Su Sun +4

Forest monitoring and education are key to forest protection, education and management, which is an effective way to measure the progress of a country's forest and climate commitme…

cs.RO2021

Active Tapping via Gaussian Process for Efficient Unknown Object Surface Reconstruction

Su Sun, Byung-Cheol Min

Object surface reconstruction brings essential benefits to robot grasping, object recognition, and object manipulation. When measuring the surface distribution of an unknown object…

cs.DB2024

MOCAS: A Multimodal Dataset for Objective Cognitive Workload Assessment on Simultaneous Tasks

Wonse Jo, Ruiqi Wang, Su Sun +3

This paper presents MOCAS, a multimodal dataset dedicated for human cognitive workload (CWL) assessment. In contrast to existing datasets based on virtual game stimuli, the data in…