ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation

• URL: http://arxiv.org/abs/2607.28581v1
• Date: Thu, 30 Jul 2026 17:40:08 GMT
• Title: ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation
• Abstract summary: High-fidelity 3D generation predominantly relies on scaling model capacity and data, which incurs prohibitive computational costs.<n>We propose ROAD, a framework that reduces the training cost of 3D generation by transferring rich discriminative priors into diffusion transformers.
• Score: 45.994649767367044
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• LoST: Level of Semantics Tokenization for 3D Shapes [50.847769883816085]
  State-of-the-art methods rely on geometric level-of-detail (LoD) hierarchies, originally designed for rendering and compression.<n>We propose Level-of-Semantics Tokenization (LoST), which orders salience, such that early prefixes decode complete, plausible shapes.<n>LoST achieves SOTA reconstruction, surpassing previous LoD-based 3D shape tokenizers by large margins on both geometric and semantic reconstruction metrics.
  arXiv  Detail & Related papers  (2026-03-18T17:56:06Z)
• FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation [50.71369329585773]
  We introduce FACE, a novel Autoregressive Autoencoder framework that generates meshes at the face level.<n>Our one-face-one-token strategy treats each triangle face, the fundamental building block of a mesh, as a single, unified token.<n> FACE achieves state-of-the-art reconstruction quality on standard benchmarks.
  arXiv  Detail & Related papers  (2026-03-02T06:47:15Z)
• PnP-U3D: Plug-and-Play 3D Framework Bridging Autoregression and Diffusion for Unified Understanding and Generation [45.72473673810981]
  We present the first unified framework for 3D understanding and generation that combines autoregression with diffusion.<n>A lightweight transformer bridges the feature space of large language models and the conditional space of 3D diffusion models.<n>Our framework achieves state-of-the-art performance across diverse 3D understanding and generation benchmarks, while also excelling in 3D editing tasks.
  arXiv  Detail & Related papers  (2026-02-03T13:49:23Z)
• GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [50.11520458252128]
  Existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data.<n>We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models.<n>GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data.
  arXiv  Detail & Related papers  (2024-12-12T17:59:03Z)
• Pushing Auto-regressive Models for 3D Shape Generation at Capacity and Scalability [118.26563926533517]
  Auto-regressive models have achieved impressive results in 2D image generation by modeling joint distributions in grid space. We extend auto-regressive models to 3D domains, and seek a stronger ability of 3D shape generation by improving auto-regressive models at capacity and scalability simultaneously.
  arXiv  Detail & Related papers  (2024-02-19T15:33:09Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.<n>We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Network [42.16520614686877]
  3D-GANs exhibit artifacts in their 3D geometrical modeling, such as mesh imperfections and holes. These shortcomings are primarily attributed to the limited availability of annotated 3D data. We present a Self-Supervised Learning technique tailored as an auxiliary loss for any 3D-GAN.
  arXiv  Detail & Related papers  (2023-12-19T04:55:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.