Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation

TL;DR

This paper addresses view inconsistency in text-to-3D generation by identifying biases in 2D diffusion models and proposing two debiasing methods, resulting in more realistic and view-consistent 3D objects.

Contribution

The paper introduces two novel debiasing approaches—score debiasing and prompt debiasing—to improve view consistency in text-to-3D generation.

Findings

Enhanced realism of 3D objects with reduced artifacts

Improved view consistency in generated 3D models

Achieved better balance between 2D fidelity and 3D coherence

Abstract

Existing score-distilling text-to-3D generation techniques, despite their considerable promise, often encounter the view inconsistency problem. One of the most notable issues is the Janus problem, where the most canonical view of an object (\textit{e.g}., face or head) appears in other views. In this work, we explore existing frameworks for score-distilling text-to-3D generation and identify the main causes of the view inconsistency problem -- the embedded bias of 2D diffusion models. Based on these findings, we propose two approaches to debias the score-distillation frameworks for view-consistent text-to-3D generation. Our first approach, called score debiasing, involves cutting off the score estimated by 2D diffusion models and gradually increasing the truncation value throughout the optimization process. Our second approach, called prompt debiasing, identifies conflicting words between user prompts and view prompts using a language model, and adjusts the discrepancy between view prompts and the viewing direction of an object. Our experimental results show that our methods improve the realism of the generated 3D objects by significantly reducing artifacts and achieve a good trade-off between faithfulness to the 2D diffusion models and 3D consistency with little overhead. Our project page is available at~\url{https://susunghong.github.io/Debiased-Score-Distillation-Sampling/}.