reconstruction quality
The fidelity of the output generated from a model compared to the original input, especially important in autoencoders and generative models. High reconstruction quality signifies that the model has accurately captured the essential features of the data.
- Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
- Dimensional Collapse in VQVAEs: Evidence and Remedies
- Event-based HDR Structured Light
- Image Super-Resolution with Guarantees via Conformalized Generative Models
- Omnidirectional 3D Scene Reconstruction from Single Image
- Solving Inverse Problems with FLAIR
- Sparse Image Synthesis via Joint Latent and RoI Flow
- TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling
- Time-Embedded Algorithm Unrolling for Computational MRI
- Understanding Bias Terms in Neural Representations
- VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption