activity
20232026
most citedMGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting

4 citations · 5 across the 25 of their papers we have counts for

collaborators
Showing 2026Show all

10 papers · 1 filter

cs.CV2026

WildHSR: Metric Feed-Forward 4D People-Scene Reconstruction from a 3D Foundation Model

Jerrin Bright, John Zelek

3D foundation models recover video cameras and geometry in one forward pass, but some of the strongest are up to scale. Joint people-scene reconstruction then requires two missing…

cs.CV2026

iVISION-2DCD: A Long-Term Change Detection Dataset for Large-Scale Outdoor Construction Monitoring

Dayou Mao, Yuchen Lin, Ashkan Ebadi +3

Automation in construction is essential for reducing costs and human errors in large-scale projects. We approach the construction progress monitoring from the aspect of detecting c…

cs.CV2026

CoGS: Compositional Dynamic Human-Object Scenes Gaussian Splatting from Monocular Video

Jerrin Bright, John Zelek

Reconstructing dynamic human--object interaction scenes from monocular video is difficult because the human, manipulated object, and background obey different motion models while s…

cs.CV2026

Latent Space Reinforcement Learning for Inverse Material Estimation in Food Fracture Simulation

Adrian Ramlal, Yuhao Chen, John S. Zelek

Realistic visual simulation of food manipulation requires accurate material parameters, yet these are difficult to measure directly and vary across the heterogeneous regions of a s…

cs.CV2026

PersistGS: Differentiable Physics for Object Permanence in 4D Gaussian Splatting

Adrian Ramlal, John S. Zelek

Dynamic 3D Gaussian Splatting (3DGS) methods reconstruct time-varying scenes from synchronized multi-camera video using photometric supervision. When a moving object becomes fully…

cs.CV2026

Beyond Static Gaussians: An Empirical Investigation of Architectural Paradigms for Dynamic 3D Scene Reconstruction

Adrian Ramlal, John S. Zelek

Dynamic scene reconstruction via 3D Gaussian Splatting (3DGS) has emerged as a compelling approach for representing evolving environments, yet understanding trade-offs between meth…

cs.CV2026

Optimizing 3D Gaussian Splatting via Point Cloud Upsampling

Adrian Ramlal, Yan Song Hu, John S. Zelek

3D Gaussian Splatting (3DGS) is a technique for creating and rendering 3D scenes, however its performance depends heavily on the quality of initial seed points. To improve 3DGS ini…

cs.CV2026

Real-Time Physics Simulation with Dynamic Mesh-Gaussian Reconstructions

Adrian Ramlal, John S. Zelek

Integrating dynamic 3D reconstructions into physics simulation requires fixed mesh topology for efficient collision detection, but state-of-the-art methods like DG-Mesh produce var…

cs.CV2026

Interpretable Pre-Release Baseball Pitch Type Anticipation from Broadcast 3D Kinematics

Jerrin Bright, Michelle Lu, John Zelek

How much can a pitcher's body reveal about the upcoming pitch? We study this question at scale by classifying eight pitch types from monocular 3D pose sequences, without access to…

cs.CV2026

Scalable Injury-Risk Screening in Baseball Pitching From Broadcast Video

Jerrin Bright, Justin Mende, John Zelek

Injury prediction in pitching depends on precise biomechanical signals, yet gold-standard measurements come from expensive, stadium-installed multi-camera systems that are unavaila…