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 131–140 of 271 papers

TitleStatusHype
Mesh Density Adaptation for Template-based Shape ReconstructionCode1
Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation—0
UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video—0
Factored-NeuS: Reconstructing Surfaces, Illumination, and Materials of Possibly Glossy Objects—0
Robust Category-Level 3D Pose Estimation from Synthetic Data—0
Eclipse: Disambiguating Illumination and Materials using Unintended Shadows—0
NOVUM: Neural Object Volumes for Robust Object ClassificationCode0
Inverse Rendering of Translucent Objects using Physical and Neural RenderersCode1
Inverse Global Illumination using a Neural Radiometric Prior—0
ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering—0
Show:102550
← PrevPage 14 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