PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
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.
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
TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking
TrackCraft3R repurposes video diffusion transformers for dense 3D tracking from monocular video, using dual-latent representation and temporal RoPE alignment to achieve state-of-the-art performance with 1.3x faster speed and 4.6x less peak memory than prior methods.
PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion
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
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.
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
MetaView proposes a diffusion-based monocular novel view synthesis framework that combines implicit geometry priors with metric depth guidance to achieve consistent and controllable rendering under large viewpoint changes from a single image.
Towards Consistent Video Geometry Estimation
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.