Ethanfel
42ebdd8b96
SGM-VFI combines local flow estimation with sparse global matching (GMFlow) to handle large motion and occlusion-heavy scenes. Adds 3 new nodes: Load SGM-VFI Model, SGM-VFI Interpolate, SGM-VFI Segment Interpolate. Architecture files vendored from MCG-NJU/SGM-VFI with device-awareness fixes (no hardcoded .cuda()), relative imports, and debug code removed. README updated with model comparison table. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
26 lines
1.1 KiB
Python
26 lines
1.1 KiB
Python
import torch
|
|
|
|
backwarp_tenGrid = {}
|
|
|
|
|
|
def clear_warp_cache():
|
|
"""Free all cached grid tensors (call between frame pairs to reclaim VRAM)."""
|
|
backwarp_tenGrid.clear()
|
|
|
|
|
|
def warp(tenInput, tenFlow):
|
|
k = (str(tenFlow.device), str(tenFlow.size()))
|
|
if k not in backwarp_tenGrid:
|
|
tenHorizontal = torch.linspace(-1.0, 1.0, tenFlow.shape[3], device=tenFlow.device).view(
|
|
1, 1, 1, tenFlow.shape[3]).expand(tenFlow.shape[0], -1, tenFlow.shape[2], -1)
|
|
tenVertical = torch.linspace(-1.0, 1.0, tenFlow.shape[2], device=tenFlow.device).view(
|
|
1, 1, tenFlow.shape[2], 1).expand(tenFlow.shape[0], -1, -1, tenFlow.shape[3])
|
|
backwarp_tenGrid[k] = torch.cat(
|
|
[tenHorizontal, tenVertical], 1).to(tenFlow.device)
|
|
|
|
tenFlow = torch.cat([tenFlow[:, 0:1, :, :] / ((tenInput.shape[3] - 1.0) / 2.0),
|
|
tenFlow[:, 1:2, :, :] / ((tenInput.shape[2] - 1.0) / 2.0)], 1)
|
|
|
|
g = (backwarp_tenGrid[k] + tenFlow).permute(0, 2, 3, 1)
|
|
return torch.nn.functional.grid_sample(input=tenInput, grid=g, mode='bilinear', padding_mode='border', align_corners=True)
|