collaborators

7 papers

cs.CV2026

OpenVO: Open-World Visual Odometry with Temporal Dynamics Awareness

Phuc D. A. Nguyen, Anh N. Nhu, Ming C. Lin

We introduce OpenVO, a novel framework for Open-world Visual Odometry (VO) with temporal awareness under limited input conditions. OpenVO effectively estimates real-world-scale ego…

cs.CV2025

MeshSplatting: Differentiable Rendering with Opaque Meshes

Jan Held, Sanghyun Son, Renaud Vandeghen +7

Primitive-based splatting methods like 3D Gaussian Splatting have revolutionized novel view synthesis with real-time rendering. However, their point-based representations remain in…

cs.CV2025

Triangle Splatting+: Differentiable Rendering with Opaque Triangles

Jan Held, Renaud Vandeghen, Sanghyun Son +6

Reconstructing 3D scenes and synthesizing novel views has seen rapid progress in recent years. Neural Radiance Fields demonstrated that continuous volumetric radiance fields can ac…

cs.CV2025

DMesh++: An Efficient Differentiable Mesh for Complex Shapes

Sanghyun Son, Matheus Gadelha, Yang Zhou +5

Recent probabilistic methods for 3D triangular meshes capture diverse shapes by differentiable mesh connectivity, but face high computational costs with increased shape details. We…

cs.CV2025

DMesh: A Differentiable Mesh Representation

Sanghyun Son, Matheus Gadelha, Yang Zhou +3

We present a differentiable representation, DMesh, for general 3D triangular meshes. DMesh considers both the geometry and connectivity information of a mesh. In our design, we fir…

cs.LG2025

Time-Aware World Model for Adaptive Prediction and Control

Anh N. Nhu, Sanghyun Son, Ming Lin

In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, Δt, and…