Latent Riemannian Flow Matching for Geometry-Grounded 3D Foundation Models
cs.CV
Submitted: 2026-07-21
Updated: 2026-11-05
Terminology
Sources
- GGBall: Graph Generative Model on Poincar'e Ball
- SceneCompleter: Dense 3D Scene Completion for Generative Novel View Synthesis
- Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking
- Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction
- Repurposing Geometric Foundation Models for Multi-view Diffusion
- Scaling View Synthesis Transformers
- MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks
- Adam: A Method for Stochastic Optimization
- Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
- Cameras as Relative Positional Encoding
- Back to Basics: Let Denoising Generative Models Denoise
- Depth Anything 3: Recovering the Visual Space from Any Views
- ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
- ProSplat: Improved Feed-Forward 3D Gaussian Splatting for Wide-Baseline Sparse Views
- VGGT-World: Transforming VGGT into an Autoregressive Geometry World Model
- GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting
- Fast protein backbone generation with SE(3) flow matching
- GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
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