CLIPortrait disentangles camera and geometry information from CLIP embeddings via 2D canonicalization, then prevents distribution collapse with a Jacobian regularizer, enabling text-guided 3D portrait generation from unlabeled 2D data.
Efficient Text-Guided 3D-Aware Portrait Generation with Score Distillation Sampling on Distribution
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Text-to-3D is an emerging task that allows users to create 3D content with infinite possibilities. Existing works tackle the problem by optimizing a 3D representation with guidance from pre-trained diffusion models. An apparent drawback is that they need to optimize from scratch for each prompt, which is computationally expensive and often yields poor visual fidelity. In this paper, we propose DreamPortrait, which aims to generate text-guided 3D-aware portraits in a single-forward pass for efficiency. To achieve this, we extend Score Distillation Sampling from datapoint to distribution formulation, which injects semantic prior into a 3D distribution. However, the direct extension will lead to the mode collapse problem since the objective only pursues semantic alignment. Hence, we propose to optimize a distribution with hierarchical condition adapters and GAN loss regularization. For better 3D modeling, we further design a 3D-aware gated cross-attention mechanism to explicitly let the model perceive the correspondence between the text and the 3D-aware space. These elaborated designs enable our model to generate portraits with robust multi-view semantic consistency, eliminating the need for optimization-based methods. Extensive experiments demonstrate our model's highly competitive performance and significant speed boost against existing methods.
citation-role summary
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation
CLIPortrait disentangles camera and geometry information from CLIP embeddings via 2D canonicalization, then prevents distribution collapse with a Jacobian regularizer, enabling text-guided 3D portrait generation from unlabeled 2D data.