SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2403.06973 · CVPR · 2024

Bayesian Diffusion Models for 3D Shape Reconstruction

Yu Lei, Xiang Zhang, U San, Yilin Wang, Yue Zhao, Zhuowen Tu, Zeyuan Chen, Haiyang Xu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes. We show the effectiveness of BDM on the 3D shape reconstruction task. Compared to prototypical deep learning data-driven approaches trained on paired (supervised) data-labels (e.g. image-point clouds) datasets, our BDM brings in rich prior information from standalone labels (e.g. point clouds) to improve the bottom-up 3D reconstruction. As opposed to the standard Bayesian frameworks where explicit prior and likelihood are required for the inference, BDM performs seamless information fusion via coupled diffusion processes with learned gradient computation networks. The specialty of our BDM lies in its capability to engage the active and effective information exchange and fusion of the top-down and bottom-up processes where each itself is a diffusion process. We demonstrate state-of-the-art results on both synthetic and realworld benchmarks for 3D shape reconstruction. Project link: https://mlpc-ucsd.github.io/BDM

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.06973")
get_code_for_paper("2403.06973")
have("2403.06973")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2403.06973.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2403.06973.svg)](https://syntology.ai/paper/2403.06973)

Connect an agent — have() is free.