Driving-scene 4D reconstruction drops dataset annotations: FreeForward4D uses only RGB video and beats STORM on Waymo full-image PSNR
FreeForward4D trains and runs on RGB driving video alone, without dataset cameras, LiDAR depth or 3D box annotations. It calibrates pretrained camera, depth and object-track predictions into one metric frame, then associates objects across cameras and models their motion on that geometry. On Waymo it reaches 27.66 dB full-image PSNR, above annotation-reliant STORM, SLARM-F, UFO, DGGT and StreetForward, while its 7.06 m depth error is higher than some annotated methods.