← Search

Zhongwei Xie

2 accepted papers

2025

SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations

ICCV 2025poster

Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of reconstructing photorealistic 3D scenes from sparse or single-vie…

Cited by 0SourcePDFScholar
2021

Boosting Ensemble Accuracy by Revisiting Ensemble Diversity Metrics

CVPR 2021poster

Neural network ensembles are gaining popularity by harnessing the complementary wisdom of multiple base models. Ensemble teams with high diversity promote high failure independence, which is effective for boosting the overall ensemble accuracy. This paper provides an in-depth study on how to design…

Cited by 54PDFcodeScholar