Sprint3D: Accelerating End-to-End 3D Asset Generation through Pipeline Optimization
cs.CV, cs.GR
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/AlayaLab/sprint3d
Project page: https://alaya-lab.github.io/sprint3d
Terminology
Sources
- Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects
- TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillation
- The Perception-Distortion Tradeoff
- Flow map matching with stochastic interpolants: A mathematical framework for consistency models
- Token Merging: Your ViT But Faster
- Token Merging for Fast Stable Diffusion
- SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
- SAM 3D: 3Dfy Anything in Images
- MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
- ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
- Objaverse: A Universe of Annotated 3D Objects
- Fast-SAM3D: 3Dfy Anything in Images but Faster
- Heat Kernel Textures: the Geodesic Gaussians That Do Not Splat
- 3D-FUTURE: 3D Furniture shape with TextURE
- Mean Flows for One-step Generative Modeling
- Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
- TABI: Tight and Balanced Interactive Atlas Packing
- AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Classifier-Free Diffusion Guidance
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