SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editing
cs.CV, cs.AI, cs.LG
Submitted: 2026-05-13
Updated: 2026-11-15
Code: https://github.com/Pointcept/Pointcept
Terminology
Sources
- Synthetic vascular structure generation for unsupervised pre-training in CTA segmentation tasks
- Vector Representations of Vessel Trees
- MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers
- Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scale
- FastMesh: Efficient Artistic Mesh Generation via Component Decoupling
- AneumoBench: A Source-Linked Benchmark for Synthetic-Geometry Transfer in Aneurysm CFD
- MeshRipple: Structured Autoregressive Generation of Artist-Meshes
- Flow Matching for Generative Modeling
- Revisiting Classifier Two-Sample Tests
- Whole Brain Vessel Graphs: A Dataset and Benchmark for Graph Learning and Neuroscience (VesselGraph)
- VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation
- Topology-Preserved Auto-regressive Mesh Generation in the Manner of Weaving Silk
- EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation
- Improving and generalizing flow-based generative models with minibatch optimal transport
- LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models
- PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance
- OPT: Open Pre-trained Transformer Language Models
- Uni3D: Exploring Unified 3D Representation at Scale
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