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

Showing 181190 of 271 papers

TitleStatusHype
PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo0
Sobolev Training for Implicit Neural Representations with Approximated Image DerivativesCode1
Self-calibrating Photometric Stereo by Neural Inverse RenderingCode1
Sparse Ellipsometry: Portable Acquisition of Polarimetric SVBRDF and Shape with Unstructured Flash PhotographyCode1
DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated ImagesCode0
GAN2X: Non-Lambertian Inverse Rendering of Image GANs0
IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor ScenesCode0
TileGen: Tileable, Controllable Material Generation and Capture0
Differentiable Rendering of Neural SDFs through Reparameterization0
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and DenoisingCode2
Show:102550
← PrevPage 19 of 28Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Neural-PBIRHDR-PSNR26.01Unverified
2NVDiffRecMCHDR-PSNR24.43Unverified
3InvRenderHDR-PSNR23.76Unverified
4NeRFactorHDR-PSNR23.54Unverified
5NeRDHDR-PSNR23.29Unverified
6NVDiffRecHDR-PSNR22.91Unverified
7PhySGHDR-PSNR21.81Unverified