AI RESEARCH
MoRGS: Efficient Per-Gaussian Motion Reasoning for Streamable Dynamic 3D Scenes
arXiv CS.CV
•
ArXi:2603.25042v1 Announce Type: new Online reconstruction of dynamic scenes aims to and real-time rendering capabilities of 3D Gaussian Splatting have made on-the-fly reconstruction practically feasible, enabling online 4D reconstruction. However, existing online approaches, despite their efficiency and visual quality, fail to learn per-Gaussian motion that reflects true scene dynamics. Without explicit motion cues, appearance and motion are optimized solely under photometric loss, causing per-Gaussian motion to chase pixel residuals rather than true 3D motion.