We propose DiffusionDepth, a new approach that reformulates monocular depth estimation as a denoising diffusion process.

Feb 28, 2023 · We formulate monocular depth estimation using denoising diffusion models, inspired by their recent successes in high fidelity image generation.

Abstract. We formulate monocular depth estimation using denoising diffusion models, inspired by their recent successes in high fidelity image generation.

Dec 4, 2023 · We introduce Marigold, a method for affine-invariant monocular depth estimation that is derived from Stable Diffusion and retains its rich prior knowledge.

We present DMD (Diffusion for Metric Depth), a state-of-the-art diffusion model for monocular absolute depth estimation.

We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection ...

We introduce a novel self-supervised depth estimation framework, dubbed MonoDiffusion, by formulating it as an iterative denoising process.

Figure 1. We present Marigold, a diffusion model and associated fine-tuning protocol for monocular depth estimation. Its core.

1. We formulate optical flow and monocular depth estimation as image to image translation with generative diffusion models, without specialized loss functions ...

This paper proposes to use diffusion models to solve monocular depth and optical flow estimation tasks. Unlike previous task-specific models for depth and flow, ...