TensoIR
A synthetic dataset for inverse rendering research, covering joint evaluation of materials, lighting and geometry. It is commonly used as a comparison benchmark for NeRF-based and 3DGS-based inverse rendering methods.
Timeline (last 90 days)
VisibilitySplat is compared against multiple classes of baselines on the TensoIR synthetic dataset, achieving competitive performance on the three tasks of novel view synthesis, albedo reconstruction, and relighting, and outperforming several earlier baselines on multiple metrics.
TensoIR is one of the commonly used synthetic benchmarks in the inverse rendering field, is based on Blender rendering, has scene geometry and materials that are all artificially constructed, and possesses precise ground truth for albedo, normals, and lighting.
All Facts (2)
VisibilitySplat is compared against multiple classes of baselines on the TensoIR synthetic dataset, achieving competitive performance on the three tasks of novel view synthesis, albedo reconstruction, and relighting, and outperforming several earlier baselines on multiple metrics.
50%UnverifiedTensoIR is one of the commonly used synthetic benchmarks in the inverse rendering field, is based on Blender rendering, has scene geometry and materials that are all artificially constructed, and possesses precise ground truth for albedo, normals, and lighting.
50%