Search papers, labs, and topics across Lattice.
This paper introduces SemanticSlider3D, a novel technique that enables continuous semantic editing of 3D objects without the need for per-attribute training. By constructing semantic editing directions in the latent space of a leading 3D generation model, the method allows users to generate a coherent range of variations for specified attributes. Validation through user studies indicates that SemanticSlider3D outperforms existing methods in terms of variation range, consistency, and overall quality, enhancing the 3D content creation process significantly.
Users can now manipulate 3D object attributes continuously and coherently without the hassle of training for each specific attribute.
Fine-grained control over continuous semantic attributes of 3D objects is essential for 3D content creation, but is not well supported by conventional 3D modeling workflows or prompt-based interaction with existing generative AI tools. While slider-based methods have proven effective for fine-grained semantic control in 2D image generation, no equivalent approach exists for 3D. Extending these 2D methods to 3D is non-trivial due to challenges unique to 3D, including geometric integrity and cross-view coherence. We present SemanticSlider3D, a technique for continuous semantic attribute editing of 3D objects that requires no per-attribute training. Given a user-specified attribute, our pipeline constructs a semantic editing direction in the latent space of a state-of-the-art 3D generation model, presenting a diverse and coherent spectrum of 3D variations. A technical validation on a dataset of 50 3D object-attribute pairs shows our method was preferred by all five human assessors across variation range, consistency, 3D object quality, and attribute disentanglement, over a baseline combining a 2D slider with an image-to-3D model. An exploratory study with six participants demonstrates that SemanticSlider3D supported decision-making in 3D prototyping and was perceived as a valuable addition to existing workflows.
