One real photo and its camera path in, a video out. The models were trained on synthetic game-engine video only; nothing here was tuned on real video.
Each scene is a handheld capture (DL3DV-10K). The model sees only the first frame and the scene's own camera path, with translations rescaled to the training speed and intrinsics fixed at 90° horizontal FOV. The real clip is shown for reference; the two are not expected to match pixel for pixel.
20 scenes, first 3 s
Direction agreement
Corr. with prescribed yaw
PSNR / LPIPS vs real
400 s model
0.93
0.79
11.7 / 0.58
200 s model
0.90
0.73
11.8 / 0.58
Repeat the first frame
–
–
12.0 / 0.55
Path following holds. Pixel agreement with the real frames is no better than repeating the first frame, so we claim path following, not fidelity.
Clip 1
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 2
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 3
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 4
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 5
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 6
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 7
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 8
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 9
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 10
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 11
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 12
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 13
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 14
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 15
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 16
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 17
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 18
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 19
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)
Clip 20
Real capture along the same camera path (4 fps)Generated from the first frame only (400 s model)