ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation
2026-07-30 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors suggest a new method called ROAD to make creating detailed 3D models cheaper and faster. Instead of starting from scratch, their method uses what existing 3D models already know about shapes and structure to guide learning. They developed a special way to align and combine different types of 3D information to ensure accuracy. Their approach works well with much less training data and cuts down the computing cost compared to standard methods.
3D generationdiffusion transformersdiscriminative modelssemantic alignmentstructural alignmentbipartite matchingfoundation modelstraining costlatent space
Authors
Xiao Luo, Mingyang Du, Xin Zhou, Tianrui Feng, Xiwu Chen, Xiaofan Li, Jiangning Zhang, Dingkang Liang
Abstract
High-fidelity 3D generation predominantly relies on scaling model capacity and data, which incurs prohibitive computational costs. This paradigm typically requires learning geometry from scratch and overlooks the rich semantic and structural priors already encapsulated in discriminative 3D foundation models. We contend that leveraging the profound understanding of the 3D world possessed by these discriminative models can significantly reduce generative cost. To this end, we propose ROAD, a framework that reduces the training cost of 3D generation by transferring these rich discriminative priors into diffusion transformers. To address the inherent semantic-structural heterogeneity between generative and discriminative latents, we introduce a reciprocal-objective alignment strategy. This method synergizes Holistic Semantic Condensing to enforce global semantic coherence and Structural Optimal Alignment, which is formulated as a bipartite matching problem to rigorously align microscopic geometric details between disparate latent spaces. The 3D foundation model is only used for training-time supervision of alignment and is not used at inference, incurring no additional inference cost. Compared with the industrial baseline Step1X-3D, the proposed ROAD achieves highly competitive generation performance with only 1.5% of the training data and significantly reduces training costs, effectively reducing the computational overhead of high-fidelity 3D generation. Code is available at https://github.com/H-EmbodVis/ROAD.