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 101–110 of 271 papers

TitleStatusHype
Eclipse: Disambiguating Illumination and Materials using Unintended Shadows—0
Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields—0
Dr.Hair: Reconstructing Scalp-Connected Hair Strands without Pre-training via Differentiable Rendering of Line Segments—0
Inverse Neural Rendering for Explainable Multi-Object Tracking—0
Inverse Global Illumination using a Neural Radiometric Prior—0
Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization—0
Deep Face Feature for Face Alignment—0
InverseFaceNet: Deep Monocular Inverse Face Rendering—0
Intrinsic PAPR for Point-level 3D Scene Albedo and Shading Editing—0
Physics-based Indirect Illumination for Inverse Rendering—0
Show:102550
← PrevPage 11 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