History-Guided Video Diffusion
- URL: http://arxiv.org/abs/2502.06764v1
- Date: Mon, 10 Feb 2025 18:44:25 GMT
- Title: History-Guided Video Diffusion
- Authors: Kiwhan Song, Boyuan Chen, Max Simchowitz, Yilun Du, Russ Tedrake, Vincent Sitzmann,
- Abstract summary: Video diffusion generates video conditioned on a variable number of context frames, collectively referred to as history.
We find two key challenges to guiding with variable-length history: architectures that only support fixed-size conditioning, and the empirical observation that CFG-style history dropout performs poorly.
We introduce History Guidance, a family of guidance methods uniquely enabled by DFoT.
- Score: 61.03681839276652
- License:
- Abstract: Classifier-free guidance (CFG) is a key technique for improving conditional generation in diffusion models, enabling more accurate control while enhancing sample quality. It is natural to extend this technique to video diffusion, which generates video conditioned on a variable number of context frames, collectively referred to as history. However, we find two key challenges to guiding with variable-length history: architectures that only support fixed-size conditioning, and the empirical observation that CFG-style history dropout performs poorly. To address this, we propose the Diffusion Forcing Transformer (DFoT), a video diffusion architecture and theoretically grounded training objective that jointly enable conditioning on a flexible number of history frames. We then introduce History Guidance, a family of guidance methods uniquely enabled by DFoT. We show that its simplest form, vanilla history guidance, already significantly improves video generation quality and temporal consistency. A more advanced method, history guidance across time and frequency further enhances motion dynamics, enables compositional generalization to out-of-distribution history, and can stably roll out extremely long videos. Website: https://boyuan.space/history-guidance
Related papers
- Making Every Frame Matter: Continuous Video Understanding for Large Models via Adaptive State Modeling [14.450847211200292]
Video understanding has become increasingly important with the rise of multi-modality applications.
We introduce a novel system, C-VUE, to overcome these issues through adaptive state modeling.
C-VUE has three key designs. The first is a long-range history modeling technique that uses a video-aware approach to retain historical video information.
The second is a spatial redundancy reduction technique, which enhances the efficiency of history modeling based on temporal relations.
arXiv Detail & Related papers (2024-10-19T05:50:00Z) - Learning Truncated Causal History Model for Video Restoration [14.381907888022615]
TURTLE learns the truncated causal history model for efficient and high-performing video restoration.
We report new state-of-the-art results on a multitude of video restoration benchmark tasks.
arXiv Detail & Related papers (2024-10-04T21:31:02Z) - TVG: A Training-free Transition Video Generation Method with Diffusion Models [12.037716102326993]
Transition videos play a crucial role in media production, enhancing the flow and coherence of visual narratives.
Recent advances in diffusion model-based video generation offer new possibilities for creating transitions but face challenges such as poor inter-frame relationship modeling and abrupt content changes.
We propose a novel training-free Transition Video Generation (TVG) approach using video-level diffusion models that addresses these limitations without additional training.
arXiv Detail & Related papers (2024-08-24T00:33:14Z) - Anchored Diffusion for Video Face Reenactment [17.343307538702238]
We introduce Anchored Diffusion, a novel method for synthesizing relatively long and seamless videos.
We train our model on video sequences with random non-uniform temporal spacing and incorporate temporal information via external guidance.
During inference, we leverage the transformer architecture to modify the diffusion process, generating a batch of non-uniform sequences anchored to a common frame.
arXiv Detail & Related papers (2024-07-21T13:14:17Z) - AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction [88.70116693750452]
Text-guided video prediction (TVP) involves predicting the motion of future frames from the initial frame according to an instruction.
Previous TVP methods make significant breakthroughs by adapting Stable Diffusion for this task.
We introduce the Multi-Modal Large Language Model (MLLM) to predict future video states based on initial frames and text instructions.
arXiv Detail & Related papers (2024-06-10T17:02:08Z) - DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance [69.0740091741732]
We propose a high-fidelity image-to-video generation method by devising a frame retention branch based on a pre-trained video diffusion model, named DreamVideo.
Our model has a powerful image retention ability and delivers the best results in UCF101 compared to other image-to-video models to our best knowledge.
arXiv Detail & Related papers (2023-12-05T03:16:31Z) - FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling [85.60543452539076]
Existing video generation models are typically trained on a limited number of frames, resulting in the inability to generate high-fidelity long videos during inference.
This study explores the potential of extending the text-driven capability to generate longer videos conditioned on multiple texts.
We propose FreeNoise, a tuning-free and time-efficient paradigm to enhance the generative capabilities of pretrained video diffusion models.
arXiv Detail & Related papers (2023-10-23T17:59:58Z) - Temporal Sentence Grounding in Streaming Videos [60.67022943824329]
This paper aims to tackle a novel task - Temporal Sentence Grounding in Streaming Videos (TSGSV)
The goal of TSGSV is to evaluate the relevance between a video stream and a given sentence query.
We propose two novel methods: (1) a TwinNet structure that enables the model to learn about upcoming events; and (2) a language-guided feature compressor that eliminates redundant visual frames.
arXiv Detail & Related papers (2023-08-14T12:30:58Z) - Just a Glimpse: Rethinking Temporal Information for Video Continual
Learning [58.7097258722291]
We propose a novel replay mechanism for effective video continual learning based on individual/single frames.
Under extreme memory constraints, video diversity plays a more significant role than temporal information.
Our method achieves state-of-the-art performance, outperforming the previous state-of-the-art by up to 21.49%.
arXiv Detail & Related papers (2023-05-28T19:14:25Z) - Video Diffusion Models [47.99413440461512]
Generating temporally coherent high fidelity video is an important milestone in generative modeling research.
We propose a diffusion model for video generation that shows very promising initial results.
We present the first results on a large text-conditioned video generation task, as well as state-of-the-art results on an established unconditional video generation benchmark.
arXiv Detail & Related papers (2022-04-07T14:08:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.