{"ID":5676738,"CreatedAt":"2026-07-03T03:29:23.032456456Z","UpdatedAt":"2026-07-14T23:57:39.674630735Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02515","arxiv_id":"2607.02515","title":"PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation","abstract":"State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage pre-trained latent diffusion models. In this work, we show that such architectural overhead and intricate loss formulations are unnecessary. We introduce a minimalist pixel-space Diffusion Transformer, built on a plain ViT, that operates directly on raw 3D point map patches and is conditioned on image tokens from a pre-trained DINOv3. Unlike existing latent diffusion approaches, we train our diffusion backbone entirely from scratch, eliminating the need for point map tokenizers. Despite its simplicity, our approach surpasses complex latent-based diffusion models while remaining significantly simpler than hybrid alternatives. Notably, it produces sharper geometric structure and is more robust in highly ambiguous regions, such as transparent objects.","short_abstract":"State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage pre-trained latent diffusion models. In this work, we show that such architectural overhead and intricate loss formulations are unnecessary....","url_abs":"https://arxiv.org/abs/2607.02515","url_pdf":"https://arxiv.org/pdf/2607.02515v1","authors":"[\"Haofei Xu\",\"Rundi Wu\",\"Philipp Henzler\",\"Nikolai Kalischek\",\"Michael Oechsle\",\"Fabian Manhardt\",\"Marc Pollefeys\",\"Andreas Geiger\",\"Federico Tombari\",\"Michael Niemeyer\"]","published":"2026-07-02T17:59:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}