PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
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 entire
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorHaofei Xu →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorRundi Wu →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorPhilipp Henzler →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorNikolai Kalischek →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorMichael Oechsle →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorFabian Manhardt →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorMarc Pollefeys →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorAndreas Geiger →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorFederico Tombari →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
- Linked via arxiv authorMichael Niemeyer →
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation