{"ID":2886880,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.02323","arxiv_id":"2508.02323","title":"Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images","abstract":"Volumetric scene reconstruction from a single image is crucial for a broad range of applications like autonomous driving and robotics. Recent volumetric reconstruction methods achieve impressive results, but generally require expensive 3D ground truth or multi-view supervision. We propose to leverage pre-trained 2D diffusion models and depth prediction models to generate synthetic scene geometry from a single image. This can then be used to distill a feed-forward scene reconstruction model. Our experiments on the challenging KITTI-360 and Waymo datasets demonstrate that our method matches or outperforms state-of-the-art baselines that use multi-view supervision, and offers unique advantages, for example regarding dynamic scenes.","short_abstract":"Volumetric scene reconstruction from a single image is crucial for a broad range of applications like autonomous driving and robotics. Recent volumetric reconstruction methods achieve impressive results, but generally require expensive 3D ground truth or multi-view supervision. We propose to leverage pre-trained 2D dif...","url_abs":"https://arxiv.org/abs/2508.02323","url_pdf":"https://arxiv.org/pdf/2508.02323v1","authors":"[\"Philipp Wulff\",\"Felix Wimbauer\",\"Dominik Muhle\",\"Daniel Cremers\"]","published":"2025-08-04T11:43:12Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}