Split-and-scale Latent 3D Representations
cs.CV
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- 3D Shape Tokenization via Latent Flow Matching
- SAM 3D: 3Dfy Anything in Images
- Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention
- SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement
- Auto-Encoding Variational Bayes
- LATTICE: Democratize High-Fidelity 3D Generation at Scale
- Fractal Generative Models
- Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling
- Flow Matching for Generative Modeling
- Velox: Learning Representations of 4D Geometry and Appearance
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
- DINOv2: Learning Robust Visual Features without Supervision
- Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
- Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation
- Extend3D: Town-Scale 3D Generation
- Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation
- Constructing a 3D Scene from a Single Image
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