PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Hugging Face Daily Papers Papers

Summary

PointDiT presents a minimalist pixel-space diffusion transformer using a plain ViT architecture for monocular geometry estimation, outperforming complex latent-based models while maintaining simplicity and robustness in ambiguous regions.

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.
Original Article
View Cached Full Text

Cached at: 07/08/26, 06:48 AM

Paper page - PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Source: https://huggingface.co/papers/2607.02515

Abstract

A minimalist pixel-space diffusion transformer using plain ViT architecture directly processes 3D point map patches conditioned on image tokens from DINOv3, outperforming complex latent-based models while maintaining simplicity and robustness in ambiguous regions.

State-of-the-art single-image 3D reconstruction methods often rely on complexhybrid architecturesandloss functions, or compress geometry into latent spaces in order to leverage pre-trainedlatent diffusion models. In this work, we show that such architectural overhead and intricate loss formulations are unnecessary. We introduce a minimalistpixel-spaceDiffusion Transformer, built on a plainViT, that operates directly on raw3D point map patchesand is conditioned on image tokens from a pre-trainedDINOv3. 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 sharpergeometric structureand is more robust in highly ambiguous regions, such astransparent objects.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.02515

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.02515 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.02515 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.02515 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

Hugging Face Daily Papers

PiD introduces a pixel diffusion decoder that reformulates latent decoding as conditional pixel diffusion, enabling fast and high-quality image synthesis at high resolutions with reduced computational requirements. It decodes latents into 4x or 8x upscaled images in under a second on consumer hardware.

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Hugging Face Daily Papers

PixWorld presents a unified pixel-space diffusion approach for 3D scene reconstruction and generation, overcoming limitations of latent-space methods by using direct image-level supervision and geometry-aware feature alignment. The method outperforms prior generation methods and matches state-of-the-art reconstruction methods.

Towards Consistent Video Geometry Estimation

Hugging Face Daily Papers

ViGeo is a transformer-based foundation model that recovers dense and consistent 3D geometry from videos using dynamic chunking attention and a completion-based data refinement framework, achieving state-of-the-art performance across multiple tasks.