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 211–220 of 271 papers

TitleStatusHype
Survey of Deep Learning Methods for Inverse Problems—0
ADOP: Approximate Differentiable One-Pixel Point RenderingCode2
Accelerating Inverse Rendering By Using a GPU and Reuse of Light Paths—0
Identity-Expression Ambiguity in 3D Morphable Face Models—0
Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting—0
Spatially and color consistent environment lighting estimation using deep neural networks for mixed reality—0
Differentiable Surface Rendering via Non-Differentiable Sampling—0
Modeling Clothing as a Separate Layer for an Animatable Human Avatar—0
Joint Learning of Portrait Intrinsic Decomposition and Relighting—0
NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning—0
Show:102550
← PrevPage 22 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