OmniLatent: Unified Latent for 3D Part Modeling
cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- LaFiTe: A Generative Latent Field for 3D Native Texturing
- PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
- MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization
- GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation
- FullPart: Generating each 3D Part at Full Resolution
- A Unified Framework for Image-to-3D Part Generation via Variable Granularity
- PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding
- Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale
- UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents
- MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion
- Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
- UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation
- CoSMo3D: Open-World Promptable 3D Semantic Part Segmentation through LLM-Guided Canonical Spatial Modeling
- LATTICE: Democratize High-Fidelity 3D Generation at Scale
- NaTex: Seamless Texture Generation as Latent Color Diffusion
- Hunyuan3D Studio: End-to-End AI Pipeline for Game-Ready 3D Asset Generation
- CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner
- TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
- MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
- Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs