{"slug": "edgar-efficient-diffusion-driven-gaussian-avatar-refinement-via-synthetic", "title": "EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure", "summary": "Researchers present EDGAR, a diffusion-driven method for refining Gaussian-splatting head avatars built from monocular video or images, targeting artifacts such as blurring, stretching and temporal instability caused by under-constrained geometry and texture. The work addresses the limits of recent Gaussian splatting approaches that have made photorealistic head avatar reconstruction efficient but not robust to sparse input constraints.", "body_md": "Recent advances in Gaussian splatting have enabled efficient and photorealistic head avatar reconstruction, yet monocular video-based or image-based methods still suffer from under-constrained geometry and texture, leading to artifacts such as blurring, stretching, and temporal instability. We prese", "url": "https://wpnews.pro/news/edgar-efficient-diffusion-driven-gaussian-avatar-refinement-via-synthetic", "canonical_source": "https://aiflash.com/news/146580/", "published_at": "2026-11-06 04:00:36+00:00", "updated_at": "2026-11-06 04:27:38.568324+00:00", "lang": "en", "topics": ["computer-vision", "generative-ai", "ai-research", "artificial-intelligence"], "entities": ["EDGAR", "Gaussian splatting"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/edgar-efficient-diffusion-driven-gaussian-avatar-refinement-via-synthetic", "markdown": "https://wpnews.pro/news/edgar-efficient-diffusion-driven-gaussian-avatar-refinement-via-synthetic.md", "text": "https://wpnews.pro/news/edgar-efficient-diffusion-driven-gaussian-avatar-refinement-via-synthetic.txt", "jsonld": "https://wpnews.pro/news/edgar-efficient-diffusion-driven-gaussian-avatar-refinement-via-synthetic.jsonld"}}