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.
One step diffusion-based super-resolution with time-aware distillation.arXiv preprint arXiv:2408.07476
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CV 4verdicts
UNVERDICTED 4roles
method 1polarities
baseline 1representative citing papers
FlowSR reformulates SR as a rectified flow and applies consistency distillation with HR regularization plus fast-slow scheduling to enable single-step high-quality super-resolution.
RealSR-R1 introduces VLCoT-GRPO with four rewards to add understanding and reasoning to real-world image super-resolution models.
Stabilizes MeanFlow for large-scale diffusion distillation via discrete warm-up and trajectory alignment, reporting better results on FLUX.1-dev and HunyuanImage 3.0.
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.
-
Fast Image Super-Resolution via Consistency Rectified Flow
FlowSR reformulates SR as a rectified flow and applies consistency distillation with HR regularization plus fast-slow scheduling to enable single-step high-quality super-resolution.
-
RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought
RealSR-R1 introduces VLCoT-GRPO with four rewards to add understanding and reasoning to real-world image super-resolution models.
-
Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion Distillation
Stabilizes MeanFlow for large-scale diffusion distillation via discrete warm-up and trajectory alignment, reporting better results on FLUX.1-dev and HunyuanImage 3.0.