Get 3D scene and segmentation using multi-step probability with VPDD
Get 3D scene and segmentation using multi-step probability with VPDD
One at A Time: Multi-step Volumetric Probability Distribution Diffusion for Depth Estimation
arXiv paper abstract https://arxiv.org/abs/2306.12681
arXiv PDF paper https://arxiv.org/pdf/2306.12681.pdf
Recent works have explored the fundamental role of depth estimation in multi-view stereo (MVS) and semantic scene completion (SSC).
They generally construct 3D cost volumes to explore geometric correspondence in depth, and estimate such volumes in a single step relying directly on the ground truth approximation.
However, such problem cannot be thoroughly handled in one step due to complex empirical distributions, especially in challenging regions like occlusions, reflections, etc.
... formulate the depth estimation task as a multi-step distribution approximation process, and introduce a new paradigm of modeling the Volumetric Probability Distribution progressively (step-by-step) following a Markov chain with Diffusion models (VPDD).
... to constrain the multi-step generation of volume in VPDD, ... construct a meta volume guidance and a confidence-aware contextual guidance as conditional geometry priors to facilitate the distribution approximation.
... VPDD outperforms the state-of-the-arts for tasks of MVS and SSC ... first camera-based work that surpasses LiDAR-based methods on the SemanticKITTI dataset.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments