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 151–160 of 271 papers

TitleStatusHype
DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse RenderingCode1
Weakly-supervised Single-view Image Relighting—0
WildLight: In-the-wild Inverse Rendering with a FlashlightCode1
Efficient Meshy Neural Fields for Animatable Human AvatarsCode1
MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting EstimationCode1
Learning a 3D Morphable Face Reflectance Model from Low-cost DataCode1
MELON: NeRF with Unposed Images in SO(3)—0
Hardware Acceleration of Neural Graphics—0
Learning Object-Centric Neural Scattering Functions for Free-Viewpoint Relighting and Scene Composition—0
Optimization-Based Eye Tracking using Deflectometric Information—0
Show:102550
← PrevPage 16 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