Align-VAE: Aligning Attention and Geometry in VecSet VAEs for 3D Reconstruction
cs.CV
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- MSVS-VAE: Multi-Scale Anchored VecSet for High-Fidelity 3D Reconstruction
- Auto-Encoding Variational Bayes
- LATTICE: Democratize High-Fidelity 3D Generation at Scale
- Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling
- Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models