3 papers
cs.CV2026
EvalMVX: A Unified Benchmarking for Neural 3D Reconstruction under Diverse Multiview Setups
Zaiyan Yang, Jieji Ren, Xiangyi Wang +5
Recent advancements in neural surface reconstruction have significantly enhanced 3D reconstruction. However, current real world datasets mainly focus on benchmarking multiview ster…
cs.CV2025
Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration
Wenjie Li, Xiangyi Wang, Heng Guo +2
Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods eith…
cs.CV2025
PMNI: Pose-free Multi-view Normal Integration for Reflective and Textureless Surface Reconstruction
Mingzhi Pei, Xu Cao, Xiangyi Wang +2
Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unre…