{"slug": "householder-motion-embedding-noise-modulation-for-motion-controllable-video", "title": "Householder Motion Embedding: Noise Modulation for Motion-Controllable Video Generation", "summary": "A new arXiv paper (2611.07294v1) proposes Householder Motion Embedding (HME), a method that encodes user-provided motion signals into diffusion noise via sequences of Householder reflections forming an orthogonal transformation on each location's channel vector. HME preserves the spatial Gaussian structure within each frame while introducing cross-frame correlations for temporal consistency, and the authors report it matches or outperforms the state of the art while achieving a 2.7x speedup over noise warping. The method is architecture-agnostic and integrates directly into standard video diffusion fine-tuning pipelines, offering an alternative to Jacobian-based distribution correction.", "body_md": "arXiv:2611.07294v1 Announce Type: new \nAbstract: Diffusion models for video generation have achieved remarkable success, yet precise motion control under explicit user guidance remains challenging. Recent noise-warping methods introduce temporal correlations by warping the noise according to the user-provided motion signal. However, standard spatial warping generally disrupts the noise's i.i.d. Gaussian structure, requiring distribution correction, such as Jacobian-based correction, but at a substantial computational overhead. We propose Householder Motion Embedding (HME), which encodes the motion signal into the noise through a sequence of Householder reflections that together form an orthogonal transformation applied to each location's channel vector. HME exactly preserves the spatial Gaussian structure within each frame while introducing cross-frame correlations that promote temporally consistent video. HME is agnostic to the network architecture and integrates directly into standard video diffusion fine-tuning pipelines. Experiments on different scenarios show that HME matches or outperforms the state of the art, while achieving a 2.7x speedup over noise warping. These results demonstrate that channel-space Householder transformations offer a principled and efficient alternative to noise warping for motion-controllable video generation.", "url": "https://wpnews.pro/news/householder-motion-embedding-noise-modulation-for-motion-controllable-video", "canonical_source": "https://arxiv.org/abs/2611.07294", "published_at": "2026-11-06 05:00:00+00:00", "updated_at": "2026-11-06 05:23:59.749931+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "ai-research", "computer-vision"], "entities": ["Householder Motion Embedding", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/householder-motion-embedding-noise-modulation-for-motion-controllable-video", "markdown": "https://wpnews.pro/news/householder-motion-embedding-noise-modulation-for-motion-controllable-video.md", "text": "https://wpnews.pro/news/householder-motion-embedding-noise-modulation-for-motion-controllable-video.txt", "jsonld": "https://wpnews.pro/news/householder-motion-embedding-noise-modulation-for-motion-controllable-video.jsonld"}}