Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution
Feiran Wang, Bin Duan, Junyi Wu +2
Video world models aim to preserve scene structure and predict how dynamic objects evolve beyond visual observations. We present Kepler4D, a framework for future video generation t…
cs.CV2026
RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction
Feiran Wang, Zezhou Shang, Gaowen Liu +1
Streaming feed-forward 3D reconstruction enables real-time joint estimation of scene geometry and camera poses from RGB images. However, without explicit dynamic reasoning, streami…