Search papers, labs, and topics across Lattice.
DreamCharacter-1 is a novel framework that fine-tunes pretrained 3D foundation models for high-fidelity character generation by integrating geometry and texture post-training along with inference acceleration. This approach enhances surface details and synthesizes high-resolution textures, leading to visually compelling and structurally robust 3D characters. Extensive experiments show that DreamCharacter-1 outperforms existing state-of-the-art methods, making it a significant advancement in the field of 3D character generation.
DreamCharacter-1 achieves unprecedented fidelity in 3D character generation, setting a new benchmark for visual realism and structural integrity.
We present DreamCharacter-1, a lightweight post-adaptation framework that calibrates pretrained 3D foundation models toward high-fidelity, production-ready 3D character generation. Building upon a 3D foundation backbone, our pipeline incorporates three task-oriented components: (1) geometry post-training, which enhances fine-grained surface details through geometric preference optimization; (2) texture post-training, which synthesizes high-resolution textures and refines the appearance of occluded regions; and (3) inference acceleration, which enables scalable deployment. Extensive quantitative and qualitative experiments demonstrate that DreamCharacter-1 produces visually compelling and structurally robust 3D character assets, consistently surpassing state-of-the-art character generation methods.
