On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise

• URL: http://arxiv.org/abs/2504.09789v2
• Date: Thu, 16 Oct 2025 05:46:47 GMT
• Title: On Equivariance and Fast Sampling in Video Diffusion Models Trained with Warped Noise
• Authors: Chao Liu, Arash Vahdat,
• Abstract summary: We show that warped noise can be trained to be equivariant to spatial transformations of the input noise.<n>This enables motion in the input noise to align naturally with motion in the generated video.<n>A further advantage is sampling efficiency: EquiVDM achieves comparable or superior quality in far fewer sampling steps.
• Score: 27.524057973734145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporally consistent video-to-video generation is critical for applications such as style transfer and upsampling. In this paper, we provide a theoretical analysis of warped noise - a recently proposed technique for training video diffusion models - and show that pairing it with the standard denoising objective implicitly trains models to be equivariant to spatial transformations of the input noise, which we term EquiVDM. This equivariance enables motion in the input noise to align naturally with motion in the generated video, yielding coherent, high-fidelity outputs without the need for specialized modules or auxiliary losses. A further advantage is sampling efficiency: EquiVDM achieves comparable or superior quality in far fewer sampling steps. When distilled into one-step student models, EquiVDM preserves equivariance and delivers stronger motion controllability and fidelity than distilled nonequivariant baselines. Across benchmarks, EquiVDM consistently outperforms prior methods in motion alignment, temporal consistency, and perceptual quality, while substantially lowering sampling cost.

Related papers

• Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models [11.913945404405865]
  Most video diffusion models (VDMs) generate videos in an autoregressive manner, generating subsequent iteration frames conditioned on previous ones.<n>We propose Adaptive Begin-of-Video Tokens (ada-BOV) for autoregressive VDMs.
  arXiv  Detail & Related papers  (2025-11-15T08:29:14Z)
• MeanFlow-Accelerated Multimodal Video-to-Audio Synthesis via One-Step Generation [12.665130073406651]
  A key challenge in synthesizing audios from silent videos is the inherent trade-off between synthesis quality and inference efficiency.<n>We introduce a MeanFlow-accelerated model that characterizes flow fields using average velocity.<n>We demonstrate that incorporating MeanFlow into the network significantly improves inference speed without compromising perceptual quality.
  arXiv  Detail & Related papers  (2025-09-08T07:15:21Z)
• A-FloPS: Accelerating Diffusion Sampling with Adaptive Flow Path Sampler [21.134678093577193]
  A-FloPS is a principled, training-free framework for flow-based generative models.<n>We show that A-FloPS consistently outperforms state-of-the-art training-free samplers in both sample quality and efficiency.<n>With as few as $5$ function evaluations, A-FloPS achieves substantially lower FID and generates sharper, more coherent images.
  arXiv  Detail & Related papers  (2025-08-22T13:28:16Z)
• M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation [65.08520614570288]
  We reformulate talking head generation into a unified framework comprising video preprocessing, motion representation, and rendering reconstruction.<n>M2DAO-Talker achieves state-of-the-art performance, with the 2.43 dB PSNR improvement in generation quality and 0.64 gain in user-evaluated video realness.
  arXiv  Detail & Related papers  (2025-07-11T04:48:12Z)
• GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering [54.489285024494855]
  Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent.<n>Existing approaches, depending on the domain they operate, suffer from several issues that degrade the user experience.<n>We introduce textbfGaVS, a novel 3D-grounded approach that reformulates video stabilization as a temporally-consistent local reconstruction and rendering' paradigm.
  arXiv  Detail & Related papers  (2025-06-30T15:24:27Z)
• Noise Conditional Variational Score Distillation [60.38982038894823]
  Noise Conditional Variational Score Distillation (NCVSD) is a novel method for distilling pretrained diffusion models into generative denoisers.<n>By integrating this insight into the Variational Score Distillation framework, we enable scalable learning of generative denoisers.
  arXiv  Detail & Related papers  (2025-06-11T06:01:39Z)
• FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation [51.110607281391154]
  FlowMo is a training-free guidance method for enhancing motion coherence in text-to-video models.<n>It estimates motion coherence by measuring the patch-wise variance across the temporal dimension and guides the model to reduce this variance dynamically during sampling.
  arXiv  Detail & Related papers  (2025-06-01T19:55:33Z)
• ReVision: High-Quality, Low-Cost Video Generation with Explicit 3D Physics Modeling for Complex Motion and Interaction [22.420752010237052]
  We introduce ReVision, a plug-and-play framework that explicitly integrates parameterized 3D physical knowledge into a conditional video generation model. We validate the effectiveness of our approach on Stable Video Diffusion, where ReVision significantly improves motion fidelity and coherence. Our results suggest that, by incorporating 3D physical knowledge, even a relatively small video diffusion model can generate complex motions and interactions with greater realism and controllability.
  arXiv  Detail & Related papers  (2025-04-30T17:59:56Z)
• FlowLoss: Dynamic Flow-Conditioned Loss Strategy for Video Diffusion Models [9.469635938429647]
  Video Diffusion Models (VDMs) can generate high-quality videos, but often struggle with producing temporally coherent motion.<n>We propose FlowLoss, which directly compares flow fields extracted from generated and ground-truth videos.<n>Our findings offer practical insights for incorporating motion-based supervision into noise-conditioned generative models.
  arXiv  Detail & Related papers  (2025-04-20T08:22:29Z)
• MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion [3.7270979204213446]
  We present four key contributions to address the challenges of video processing.<n>First, we introduce the 3D Inverted Vector-Quantization Variencoenco Autocoder.<n>Second, we present MotionAura, a text-to-video generation framework.<n>Third, we propose a spectral transformer-based denoising network.<n>Fourth, we introduce a downstream task of Sketch Guided Videopainting.
  arXiv  Detail & Related papers  (2024-10-10T07:07:56Z)
• SF-V: Single Forward Video Generation Model [57.292575082410785]
  We propose a novel approach to obtain single-step video generation models by leveraging adversarial training to fine-tune pre-trained models. Experiments demonstrate that our method achieves competitive generation quality of synthesized videos with significantly reduced computational overhead.
  arXiv  Detail & Related papers  (2024-06-06T17:58:27Z)
• ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation [81.90265212988844]
  We propose a training-free video method for generative video models in a plug-and-play manner. We transform a video model into a self-cascaded video diffusion model with the designed hidden state correction modules. Our training-free method is even comparable to trained models supported by huge compute resources and large-scale datasets.
  arXiv  Detail & Related papers  (2024-06-03T00:31:13Z)
• Score-based Generative Models with Adaptive Momentum [40.84399531998246]
  We propose an adaptive momentum sampling method to accelerate the transforming process. We show that our method can produce more faithful images/graphs in small sampling steps with 2 to 5 times speed up.
  arXiv  Detail & Related papers  (2024-05-22T15:20:27Z)
• Boosting Diffusion Models with Moving Average Sampling in Frequency Domain [101.43824674873508]
  Diffusion models rely on the current sample to denoise the next one, possibly resulting in denoising instability. In this paper, we reinterpret the iterative denoising process as model optimization and leverage a moving average mechanism to ensemble all the prior samples. We name the complete approach "Moving Average Sampling in Frequency domain (MASF)"
  arXiv  Detail & Related papers  (2024-03-26T16:57:55Z)
• GenDeF: Learning Generative Deformation Field for Video Generation [89.49567113452396]
  We propose to render a video by warping one static image with a generative deformation field (GenDeF) Such a pipeline enjoys three appealing advantages.
  arXiv  Detail & Related papers  (2023-12-07T18:59:41Z)
• EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation [57.539634387672656]
  Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without sacrificing quality. We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation.
  arXiv  Detail & Related papers  (2023-12-04T18:58:38Z)
• VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models [58.93124686141781]
  Video Motion Customization (VMC) is a novel one-shot tuning approach crafted to adapt temporal attention layers within video diffusion models. Our approach introduces a novel motion distillation objective using residual vectors between consecutive frames as a motion reference. We validate our method against state-of-the-art video generative models across diverse real-world motions and contexts.
  arXiv  Detail & Related papers  (2023-12-01T06:50:11Z)
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets [36.95521842177614]
  We present Stable Video Diffusion - a latent video diffusion model for high-resolution, state-of-the-art text-to-video and image-to-video generation. We identify and evaluate three different stages for successful training of video LDMs: text-to-image pretraining, video pretraining, and high-quality video finetuning.
  arXiv  Detail & Related papers  (2023-11-25T22:28:38Z)
• LaMD: Latent Motion Diffusion for Image-Conditional Video Generation [63.34574080016687]
  latent motion diffusion (LaMD) framework consists of a motion-decomposed video autoencoder and a diffusion-based motion generator. LaMD generates high-quality videos on various benchmark datasets, including BAIR, Landscape, NATOPS, MUG and CATER-GEN.
  arXiv  Detail & Related papers  (2023-04-23T10:32:32Z)
• ShiftDDPMs: Exploring Conditional Diffusion Models by Shifting Diffusion Trajectories [144.03939123870416]
  We propose a novel conditional diffusion model by introducing conditions into the forward process. We use extra latent space to allocate an exclusive diffusion trajectory for each condition based on some shifting rules. We formulate our method, which we call textbfShiftDDPMs, and provide a unified point of view on existing related methods.
  arXiv  Detail & Related papers  (2023-02-05T12:48:21Z)
• Diffusion Glancing Transformer for Parallel Sequence to Sequence Learning [52.72369034247396]
  We propose the diffusion glancing transformer, which employs a modality diffusion process and residual glancing sampling. DIFFGLAT achieves better generation accuracy while maintaining fast decoding speed compared with both autoregressive and non-autoregressive models.
  arXiv  Detail & Related papers  (2022-12-20T13:36:25Z)
• VIDM: Video Implicit Diffusion Models [75.90225524502759]
  Diffusion models have emerged as a powerful generative method for synthesizing high-quality and diverse set of images. We propose a video generation method based on diffusion models, where the effects of motion are modeled in an implicit condition. We improve the quality of the generated videos by proposing multiple strategies such as sampling space truncation, robustness penalty, and positional group normalization.
  arXiv  Detail & Related papers  (2022-12-01T02:58:46Z)
• Latent Video Diffusion Models for High-Fidelity Long Video Generation [58.346702410885236]
  We introduce lightweight video diffusion models using a low-dimensional 3D latent space. We also propose hierarchical diffusion in the latent space such that longer videos with more than one thousand frames can be produced. Our framework generates more realistic and longer videos than previous strong baselines.
  arXiv  Detail & Related papers  (2022-11-23T18:58:39Z)

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.