paper-with-me

홈 › Papers

IV-Mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis

2024-10-05 · Shitong Shao, Zikai Zhou, Lichen Bai, Haoyi Xiong, Zeke Xie

The multi-step sampling mechanism, a key feature of visual diffusion models, has significant potential to replicate the success of OpenAI's Strawberry in enhancing performance by increasing the inference computational cost. Sufficient prior studies have demonstrated that correctly scaling up computation in the sampling process can successfully lead to improved generation quality, enhanced image editing, and compositional generalization. While there have been rapid advancements in developing inference-heavy algorithms for improved image generation, relatively little work has explored inference scaling laws in video diffusion models (VDMs). Furthermore, existing research shows only minimal performance gains that are perceptible to the naked eye. To address this, we design a novel training-free algorithm IV-Mixed Sampler that leverages the strengths of image diffusion models (IDMs) to assist VDMs surpass their current capabilities. The core of IV-Mixed Sampler is to use IDMs to significantly enhance the quality of each video frame and VDMs ensure the temporal coherence of the video during the sampling process. Our experiments have demonstrated that IV-Mixed Sampler achieves state-of-the-art performance on 4 benchmarks including UCF-101-FVD, MSR-VTT-FVD, Chronomagic-Bench-150, and Chronomagic-Bench-1649. For example, the open-source Animatediff with IV-Mixed Sampler reduces the UMT-FVD score from 275.2 to 228.6, closing to 223.1 from the closed-source Pika-2.0.

📄 PDF Abstract BibTeX arXiv:2410.04171

Code (1)

xie-lab-ml/IV-mixed-Sampler 공식 구현 pytorch

Tasks

Text-to-Video Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Progressive Tempering Sampler with Diffusion

2025-06-05 · Severi Rissanen, Ruikang Ouyang, Jiajun He, Wenlin Chen 외

Recent research has focused on designing neural samplers that amortize the process of sampling from unnormalized densities. However, despite significant advancements, they still fall short of the state-of-the-art MCMC ap…

Co-learning Single-Step Diffusion Upsampler and Downsampler with Two Discriminators and Distillation

2024-10-10 · Sohwi Kim, Tae-Kyun Kim

Super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, often relying on effective downsampling to generate diverse and realistic training pairs. In this work, w…

Image ReconstructionSuper-Resolution

Boosting Diffusion Models with an Adaptive Momentum Sampler

2023-08-23 · Xiyu Wang, Anh-Dung Dinh, Daochang Liu, Chang Xu

Diffusion probabilistic models (DPMs) have been shown to generate high-quality images without the need for delicate adversarial training. However, the current sampling process in DPMs is prone to violent shaking. In this…

Understanding Sampler Stochasticity in Training Diffusion Models for RLHF

2025-10-12 · Jiayuan Sheng, Hanyang Zhao, Haoxian Chen, David D. Yao 외 arxiv

Reinforcement Learning from Human Feedback (RLHF) is increasingly used to fine-tune diffusion models, but a key challenge arises from the mismatch between stochastic samplers used during training and deterministic sample…

Reinforcement Learning

RBF-Solver: A Multistep Sampler for Diffusion Probabilistic Models via Radial Basis Functions

2026-03-05 · Soochul Park, Yeon Ju Lee, SeongJin Yoon, Jiyub Shin 외 arxiv

Diffusion probabilistic models (DPMs) are widely adopted for their outstanding generative fidelity, yet their sampling is computationally demanding. Polynomial-based multistep samplers mitigate this cost by accelerating …