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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 41–50 of 271 papers

TitleStatusHype
Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion ModelCode1
IBL-NeRF: Image-Based Lighting Formulation of Neural Radiance FieldsCode1
Efficient Meshy Neural Fields for Animatable Human AvatarsCode1
Inverse Rendering of Translucent Objects using Physical and Neural RenderersCode1
Diffusion Posterior Illumination for Ambiguity-aware Inverse RenderingCode1
InverseRenderNet: Learning single image inverse renderingCode1
Dynamic Scene Understanding through Object-Centric Voxelization and Neural RenderingCode1
DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse RenderingCode1
Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting EstimationCode1
Learning Inverse Rendering of Faces from Real-world VideosCode1
Show:102550
← PrevPage 5 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