FuguReport

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Authors Haofei Xu, Rundi Wu, Philipp Henzler, Nikolai Kalischek, Michael Oechsle, Fabian Manhardt, Marc Pollefeys, Andreas Geiger, Federico Tombari, Michael Niemeyer
Affiliations Max Planck Institute for Intelligent Systems / University of Tübingen / Google / Technical University of Munich / ETH Zurich / Microsoft
Categories Method / Diffusion Models / Pixel-space diffusion for 3D points, Application / 3D Reconstruction / Single-image 3D geometry estimation, Method / Vision Transformer / Minimal ViT architecture for geometry
License CC BY 4.0

Abstract Overview

PointDiT formulates monocular geometry estimation as conditional pixel-space diffusion over dense 3D point maps rather than deterministic regression or latent diffusion. The model is intentionally simple: a plain Vision Transformer operates directly on raw point-map patches and is conditioned on frozen DINOv3 image tokens, while training uses flow matching with clean point-map prediction. The paper also introduces task-specific handling for point-map normalization and sky regions so indoor and outdoor data can be trained jointly. Experiments evaluate zero-shot transfer from synthetic-only training to seven real-world datasets and analyze single-step, multi-step, and ablated variants.

Novelty

The main novelty is applying a minimalist pixel-space diffusion transformer directly to monocular point-map prediction, avoiding both VAE-based latent tokenization and the hybrid architectures common in prior geometry systems. The work further argues that clean-data (x-prediction) is crucial for 3D point-map diffusion and shows that this setup can support competitive one-step inference.

Results

On seven real-world evaluation datasets, PointDiT-H achieves the best reported depth metrics in the comparison table (Rel_d 2.75 and δ1_d 98.54 with multi-step inference) and the highest boundary sharpness BF1 of 10.49, while MoGe remains slightly better on point-map Rel_p (4.21 vs. 4.40). Even one-step PointDiT-H already exceeds prior methods on BF1 (9.79 vs. best baseline 9.41) and is much faster than GeometryCrafter at single-step inference (72 ms vs. 1,178 ms). Additional diffusion steps mainly refine boundaries, and controlled experiments show the generative formulation improves BF1 over a matched deterministic regressor (13.92 vs. 10.90).

Key Points

  1. PointDiT uses a plain ViT to diffuse directly in raw 3D point-map space, conditioned by multi-layer DINOv3 features, instead of relying on latent VAEs or complex hybrid geometry architectures.
  2. The method is trained largely with flow matching plus a lightweight relative point loss, and its ablations show that clean point-map prediction (x-prediction) is critical while direct velocity prediction performs poorly.
  3. Synthetic-only training transfers zero-shot to seven real-world datasets, where the model delivers especially strong geometric boundary quality and supports both efficient one-step inference and further multi-step refinement.

References

This page was created using generative AI such as GPT-5, Claude Opus 4, Gemini 3, Gemini 3.1 Flash Image, and their higher-end successor versions. No guarantee can be made regarding its contents.