Zero-Shot Novel Depth Synthesis Using 3D Foundation Model Scene Representations

Fri, 28 Aug 2026 00:00:00 +0000

Zero-Shot Novel Depth Synthesis Using 3D Foundation Model Scene Representations

Z3D is a zero-shot framework for novel-view depth synthesis that combines 3D foundation model scene representations with a diffusion model to predict depth from sparse source views.

Given source images and the relative pose of a target view, Z3D first extracts a scene representation from the source views using a pretrained 3D foundation model. The resulting representation is then used to synthesize the depth of the target view without requiring target-view depth supervision.

Project Page · Code

Depth Estimation | Denis Mbey Akola

Zero-Shot Novel Depth Synthesis Using 3D Foundation Model Scene Representations

Zero-Shot Novel Depth Synthesis Using 3D Foundation Model Scene Representations