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 21–30 of 271 papers

TitleStatusHype
Uncertainty for SVBRDF Acquisition using Frequency AnalysisCode1
Spin-UP: Spin Light for Natural Light Uncalibrated Photometric StereoCode1
High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse RenderingCode1
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray TracingCode1
GIR: 3D Gaussian Inverse Rendering for Relightable Scene FactorizationCode1
The Sky's the Limit: Re-lightable Outdoor Scenes via a Sky-pixel Constrained Illumination Prior and Outside-In VisibilityCode1
RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination PriorCode1
Stanford-ORB: A Real-World 3D Object Inverse Rendering BenchmarkCode1
SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance ScenesCode1
Diffusion Posterior Illumination for Ambiguity-aware Inverse RenderingCode1
Show:102550
← PrevPage 3 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