Score Distillation Sampling (SDS) enables 3D asset generation by distilling priors from pretrained 2D text-to-image diffusion models, but vanilla SDS suffers from over-saturation and over-smoothing. To mitigate this issue, recent variants have incorporated negative prompts. However, these methods face a critical trade-off: limited texture optimization, or significant texture gains with shape distortion. In this work, we first conduct a systematic analysis and reveal that this trade-off is fundamentally governed by the utilization of the negative prompts, where Target Negative Prompts (TNP) that embed target information in the negative prompts dramatically enhancing texture realism and fidelity but inducing shape distortions. Informed by this key insight, we introduce the Target-Balanced Score Distillation (TBSD). It formulates generation as a multi-objective optimization problem and introduces an adaptive strategy that effectively resolves the aforementioned trade-off. Extensive experiments demonstrate that TBSD significantly outperforms existing state-of-the-art methods, yielding 3D assets with high-fidelity textures and geometrically accurate shape.

We present a complete framework for synthesizing style-preserving 2D cartoons by learning from traditional Chinese cartoons. In contrast to reusing-based approaches which rely on rearranging or retrieving existing cartoon sequences, we aim to generate stylized cartoons with the idea of style factorization. Specifically, starting with 2D skeleton features of cartoon characters extracted by an improved rotoscoping system, we present a non-negative style factorization (NNSF) algorithm to obtain style basis and weights and simultaneously preserve class separability. Thus, factorized style basis can be combined with heterogeneous weights to re-synthesize style-preserving features, and then these features are used as the driving source in the character reshaping process via our proposed subkey-driving strategy. Extensive experiments and examples demonstrate the effectiveness of the proposed framework.

Abstract Traditional pose similarity functions based on joint coordinates or rotations often do not conform to human perception. We propose a new perceptual pose distance:Relational Geometric Distancethat accumulates the differences over a set of features that reflects the geometric relations between different body parts. An extensive relational geometric feature pool that contains a large number of potential features is defined, and the features effective for pose similarity estimation are selected using a set of labeled data by Adaboost. The extensive feature pool guarantees that a wide diversity of features is considered, and the boosting ensures that the selected features are optimized when used jointly. Finally, the selected features form a pose distance function that can be used for novel poses. Experiments show that our method outperforms others in emulating human perception in pose similarity. Our method can also adapt to specific motion types and capture the features that are important for pose similarity of a certain motion type. Copyright © 2009 John Wiley & Sons, Ltd.