Connexion
Idée - Neural Surface Reconstruction
Pose Residual Field for Neural Surface Reconstruction at ICLR 2024
Introducing PoRF for accurate camera pose refinement in neural surface reconstruction.
NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering
Recovering geometry, material properties, and illumination from multi-view images using NeuS-PIR method.
NeuS-PIR: Learning Relightable Neural Surface using Pre-Integrated Rendering
Recovering relightable neural surfaces using pre-integrated rendering for advanced applications.
UFORecon: Generalizable Sparse-View Surface Reconstruction Framework
UFORecon proposes a robust view-combination generalizable surface reconstruction framework, outperforming existing methods in both favorable and unfavorable view-combinations.
UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Data Sets
UFORecon verbessert die Generalisierbarkeit der Oberflächenrekonstruktion durch robuste Ansätze für unterschiedliche Kamerakombinationen.