← Search

Zaifeng Yang

7 accepted papers

2025

NCDI-Diffusion: Neural Contextual and Directional Inversion for Novel View Synthesis through Diffusion Models

ICASSP 2025accepted

Novel view synthesis typically requires a comprehensive set of multi-view images for either image-based rendering or scene representation-based optimization. However, achieving high-fidelity novel view rendering often demands a large number of images. To address this limitation, we propose NCDI-Diff…

Cited by 0SourceScholar
2025

PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary Learning

ICML 2025spotlight

This paper presents a novel approach to hyperspectral image (HSI) reconstruction from RGB images, addressing fundamental limitations in existing learning-based methods from a physical perspective. We discuss and aim to address the ``colorimetric dilemma": failure to consistently reproduce ground-tru…

Cited by 0SourcePDFScholar
2025

Unraveling Metameric Dilemma for Spectral Reconstruction: A High-Fidelity Approach via Semi-Supervised Learning

NeurIPS 2025poster

Spectral reconstruction from RGB images often suffers from a metameric dilemma, where distinct spectral distributions map to nearly identical RGB values, making them indistinguishable to current models and leading to unreliable reconstructions. In this paper, we present Diff-Spectra that integrates…

Cited by 0SourceScholar
2024

Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues

AAAI 2024technical

Existing learning-based hyperspectral reconstruction methods show limitations in fully exploiting the information among the hyperspectral bands. As such, we propose to investigate the chromatic inter-dependencies in their respective hyperspectral embedding space. These embedded features can be fully…

2021

A Multi-Stage Progressive Learning Strategy for Covid-19 Diagnosis Using Chest Computed Tomography with Imbalanced Data

ICASSP 2021accepted

In this paper, a multi-stage progressive learning strategy is investigated to train classifiers for COVID-19 Diagnosis using imbalanced Chest Computed Tomography Data acquired from patients infected with COVID-19 Pneumonia, Community Acquired Pneumonia (CAP) and from normal healthy subjects. In the…

Cited by 0SourceScholar