Research map / 3D vision / 3D generation
Bridging 1D, 2D, and 3D with Any-to-Any Multimodal Modeling
Jason Toskov, Oriol Barbany, Rishubh Singh, Jinya Sakurai, Efe Tarhan, Oğuzhan F Kar, Roman Bachmann, Amir Zadeh, Jesse Allardice, Chuan Li, Carme Torras, Afshin Dehghan and 1 more
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Presents OmniDiMM, an any-to-any foundation model that natively handles 1D, 2D, and 3D modalities, trained on a diverse set of 3D data including meshes.
Problem
Existing large-scale multimodal models are built mostly around 1D, 2D and 2.5D modalities, lacking native 3D understanding and generation.
Approach
An any-to-any foundation model that natively models and generates across 1D, 2D, and 3D modalities, trained on diverse 3D data including meshes.
Closest papers by meaning
- ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding (NeurIPS 2025 · similarity 0.87)
- 4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities (NeurIPS 2024 · similarity 0.87)
- Large-Vocabulary 3D Diffusion Model with Transformer (ICLR 2024 · similarity 0.86)
- ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding (CVPR 2024 · similarity 0.86)
- Uni3D: Exploring Unified 3D Representation at Scale (ICLR 2024 · similarity 0.86)
- Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning (CVPR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
