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 231–240 of 271 papers

TitleStatusHype
Building 3D Morphable Models from a Single ScanCode1
Modular Primitives for High-Performance Differentiable RenderingCode2
MaterialGAN: Reflectance Capture using a Generative SVBRDF Model—0
Invertible Neural BRDF for Object Inverse RenderingCode1
Object-based Illumination Estimation with Rendering-aware Neural Networks—0
Single-Shot Neural Relighting and SVBRDF Estimation—0
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets—0
Polarimetric Multi-View Inverse Rendering—0
Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion ModelCode1
Q-NET: A Network for Low-Dimensional Integrals of Neural Proxies—0
Show:102550
← PrevPage 24 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