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 1–25 of 271 papers

TitleStatusHype
Segment Anything in 3D with Radiance FieldsCode3
Colorful Diffuse Intrinsic Image Decomposition in the WildCode3
Inferring Articulated Rigid Body Dynamics from RGBD VideoCode3
Modular Primitives for High-Performance Differentiable RenderingCode2
GS-IR: 3D Gaussian Splatting for Inverse RenderingCode2
Intrinsic Image Decomposition via Ordinal ShadingCode2
Extracting Triangular 3D Models, Materials, and Lighting From ImagesCode2
TensoIR: Tensorial Inverse RenderingCode2
Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object RelightingCode2
ADOP: Approximate Differentiable One-Pixel Point RenderingCode2
Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and DenoisingCode2
Advances in Neural RenderingCode1
A Morphable Face Albedo ModelCode1
Uncertainty for SVBRDF Acquisition using Frequency AnalysisCode1
DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse RenderingCode1
GIR: 3D Gaussian Inverse Rendering for Relightable Scene FactorizationCode1
IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View SynthesisCode1
A Level Set Theory for Neural Implicit Evolution under Explicit FlowsCode1
Dynamic Scene Understanding through Object-Centric Voxelization and Neural RenderingCode1
Building 3D Morphable Models from a Single ScanCode1
Efficient Meshy Neural Fields for Animatable Human AvatarsCode1
Multiview Textured Mesh Recovery by Differentiable RenderingCode1
Differentiable Programming for Hyperspectral Unmixing using a Physics-based Dispersion ModelCode1
A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse RenderingCode1
High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse RenderingCode1
Show:102550
← PrevPage 1 of 11Next →

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