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 211–220 of 271 papers

TitleStatusHype
Differentiable Neural Radiosity—0
Differentiable Point-based Inverse Rendering—0
Differentiable Rendering of Neural SDFs through Reparameterization—0
Differentiable Surface Rendering via Non-Differentiable Sampling—0
Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance—0
Diffusion Renderer: Neural Inverse and Forward Rendering with Video Diffusion Models—0
DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models—0
Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset—0
Physics-based Indirect Illumination for Inverse Rendering—0
Dressi: A Hardware-Agnostic Differentiable Renderer with Reactive Shader Packing and Soft Rasterization—0
Show:102550
← PrevPage 22 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