SOTAVerified

Inverse Rendering

Inverse Rendering is the task of recovering the properties of a scene, such as shape, material, and lighting, from an image or a video. The goal of inverse rendering is to determine the properties of a scene given an observation of it, and to generate new images or videos based on these properties.

Papers

Showing 81–90 of 271 papers

TitleStatusHype
Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes—0
GroomLight: Hybrid Inverse Rendering for Relightable Human Hair Appearance Modeling—0
SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation—0
Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior—0
GlossGau: Efficient Inverse Rendering for Glossy Surface with Anisotropic Spherical Gaussian—0
Generative Detail Enhancement for Physically Based Materials—0
OMG: Opacity Matters in Material Modeling with Gaussian Splatting—0
NPSim: Nighttime Photorealistic Simulation From Daytime Images With Monocular Inverse Rendering and Ray Tracing—0
Multi-view 3D surface reconstruction from SAR images by inverse rendering—0
DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models—0
Show:102550
← PrevPage 9 of 28Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Neural-PBIRHDR-PSNR26.01—Unverified
2NVDiffRecMCHDR-PSNR24.43—Unverified
3InvRenderHDR-PSNR23.76—Unverified
4NeRFactorHDR-PSNR23.54—Unverified
5NeRDHDR-PSNR23.29—Unverified
6NVDiffRecHDR-PSNR22.91—Unverified
7PhySGHDR-PSNR21.81—Unverified