ChopGrad truncates backpropagation to local frame windows in video diffusion models, reducing memory from linear in frame count to constant while enabling pixel-wise loss fine-tuning.
In: Proceedings of the IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation
ChopGrad truncates backpropagation to local frame windows in video diffusion models, reducing memory from linear in frame count to constant while enabling pixel-wise loss fine-tuning.