{"slug": "pixgr-pixel-space-generative-decoding-for-fast-feed-forward-3d-reconstruction", "title": "PixGR: Pixel-Space Generative Decoding for Fast Feed-Forward 3D Reconstruction", "summary": "Researchers released PixGR, a framework that adds lightweight pixel-space generative modeling to feed-forward 3D Gaussian reconstruction, detailed in arXiv paper 2610.31908v1. PixGR encodes context observations once into a scene latent, then uses pixel-space flow matching with a lightweight DiT decoder to generate a shared 3D Gaussian representation, avoiding VAE-based latent compression and the error propagation of two-stage pipelines. The authors report PixGR outperforms regression-based approaches in sparse-view settings, including widely spaced observations and view extrapolation, while maintaining sub-second inference and remaining competitive with substantially heavier pretrained generative models.", "body_md": "arXiv:2610.31908v1 Announce Type: new \nAbstract: We present PixGR, an efficient framework that integrates lightweight pixel-space generative modeling into feed-forward 3D Gaussian reconstruction to model scene uncertainty. Context observations are encoded once into a scene latent representation, which conditions generative decoding from noisy target views to produce a shared 3D Gaussian representation. We formulate this process using pixel-space flow matching, enabling end-to-end optimization of 3D reconstruction with direct pixel-space generative supervision through differentiable rendering. This avoids VAE-based latent compression and error propagation inherent in previous two-stage pipelines. To preserve feed-forward efficiency, PixGR caches the scene representation and performs iterative inference using a lightweight DiT decoder. Experiments demonstrate that PixGR outperforms regression-based approaches in challenging sparse-view settings, particularly with widely spaced observations and view extrapolation. Meanwhile, it maintains sub-second inference and remains competitive with substantially heavier pretrained generative models. Our project page is available at https://ranrhuang.github.io/pixgr/.", "url": "https://wpnews.pro/news/pixgr-pixel-space-generative-decoding-for-fast-feed-forward-3d-reconstruction", "canonical_source": "https://arxiv.org/abs/2610.31908", "published_at": "2026-10-26 04:00:00+00:00", "updated_at": "2026-10-26 04:12:18.347543+00:00", "lang": "en", "topics": ["computer-vision", "generative-ai", "ai-research", "machine-learning"], "entities": ["PixGR", "arXiv", "DiT"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/pixgr-pixel-space-generative-decoding-for-fast-feed-forward-3d-reconstruction", "markdown": "https://wpnews.pro/news/pixgr-pixel-space-generative-decoding-for-fast-feed-forward-3d-reconstruction.md", "text": "https://wpnews.pro/news/pixgr-pixel-space-generative-decoding-for-fast-feed-forward-3d-reconstruction.txt", "jsonld": "https://wpnews.pro/news/pixgr-pixel-space-generative-decoding-for-fast-feed-forward-3d-reconstruction.jsonld"}}