Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

Inverse Rendering

3260 papers • 126 benchmarks • 313 datasets

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.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in inverse-rendering

Trend

Dataset

Best Model

Actions

Stanford-ORB

Stanford-ORB

Libraries

i

Use these libraries to find inverse-rendering models and implementations

Datasets

Hypersim

Stanford-ORB

MID Intrinsics

Subtasks

No subtasks available.

Most implemented papers

Approximate Differentiable Rendering with Algebraic Surfaces

M. Hebert, L. Keselman•Wed Jul 20 2022

This work develops an approximate differentiable renderer for a compact, interpretable representation, which it is shown that the method is the only one comparable to classic techniques for pose estimation, and performs well in shape from silhouette.

53

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

0

Extracting Triangular 3D Models, Materials, and Lighting From Images

S. Fidler, Alex Evans, T. Müller, Wenzheng Chen, Jun Gao, Jacob Munkberg, J. Hasselgren, Tianchang Shen•Tue Nov 23 2021

This work outputs triangle meshes with spatially-varying materials and environment lighting that can be deployed in any traditional graphics engine unmodified, and introduces a differentiable formulation of the split sum approximation of environment lighting to efficiently recover all-frequency lighting.

460 0

SfSNet: Learning Shape, Reflectance and Illuminance of Faces 'in the Wild'

Angjoo Kanazawa, C. Castillo, Soumyadip Sengupta, D. Jacobs•Fri Dec 01 2017

SfSNet produces significantly better quantitative and qualitative results than state-of-the-art methods for inverse rendering and independent normal and illumination estimation and is designed to reflect a physical lambertian rendering model.

337 0

Differentiable Monte Carlo ray tracing through edge sampling

F. Durand, J. Lehtinen, M. Aittala, Tzu-Mao Li•Mon Dec 03 2018

This work introduces a general-purpose differentiable ray tracer, which is the first comprehensive solution that is able to compute derivatives of scalar functions over a rendered image with respect to arbitrary scene parameters such as camera pose, scene geometry, materials, and lighting parameters.

553 0

Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image

Manmohan Chandraker, R. Ramamoorthi, Kalyan Sunkavalli, Zhengqin Li, Mohammad Shafiei•Mon May 06 2019

A deep inverse rendering framework for indoor scenes, which combines novel methods to map complex materials to existing indoor scene datasets and a new physically-based GPU renderer to create a large-scale, photorealistic indoor dataset.

305 0

Deep Single-Image Portrait Relighting

Kalyan Sunkavalli, D. Jacobs, Hao Zhou, Sunil Hadap•Mon Sep 30 2019

Conventional physically-based methods for relighting portrait images need to solve an inverse rendering problem, estimating face geometry, reflectance and lighting. However, the inaccurate estimation of face components can cause strong artifacts in relighting, leading to unsatisfactory results. In this work, we apply a physically-based portrait relighting method to generate a large scale, high quality, “in the wild” portrait relighting dataset (DPR). A deep Convolutional Neural Network (CNN) is then trained using this dataset to generate a relit portrait image by using a source image and a target lighting as input. The training procedure regularizes the generated results, removing the artifacts caused by physically-based relighting methods. A GAN loss is further applied to improve the quality of the relit portrait image. Our trained network can relight portrait images with resolutions as high as 1024 × 1024. We evaluate the proposed method on the proposed DPR datset, Flickr portrait dataset and Multi-PIE dataset both qualitatively and quantitatively. Our experiments demonstrate that the proposed method achieves state-of-the-art results. Please refer to https://zhhoper.github.io/dpr.html for dataset and code.

241 0

Differentiable surface splatting for point-based geometry processing

Yifan Wang, Felice Serena, Shihao Wu, Cengiz Öztireli, O. Sorkine-Hornung•Sun Jun 09 2019

Applications of DSS to inverse rendering for geometry synthesis and denoising, where large scale topological changes, as well as small scale detail modifications, are accurately and robustly handled without requiring explicit connectivity, outperforming state-of-the-art techniques are demonstrated.

358 0

InverseRenderNet: Learning Single Image Inverse Rendering

Ye Yu, W. Smith•Wed Nov 28 2018

This work shows how to train a fully convolutional neural network to perform inverse rendering from a single, uncontrolled image, and believes this is the first attempt to use MVS supervision for learning inverse rendering.

175 0

Intrinsic Image Decomposition via Ordinal Shading

Chris Careaga, Yağız Aksoy•Fri Oct 27 2023

A straightforward method for generating dense pseudo ground truth using the model’s predictions and multi-illumination data, enabling generalization to in-the-wild imagery and the real-world applicability of the estimations by performing otherwise difficult editing tasks such as recoloring and relighting is demonstrated.

59 0

RenderNet: A deep convolutional network for differentiable rendering from 3D shapes

Thu Nguyen-Phuoc, Chuan Li, Yong-Liang Yang, Stephen Balaban•Sun Jun 17 2018

RenderNet is presented, a differentiable rendering convolutional network with a novel projection unit that can render 2D images from 3D shapes with high performance and can be used in inverse rendering tasks to estimate shape, pose, lighting and texture from a single image.

160 0

Adding a benchmark result helps the community track progress.

Inverse Rendering | State-of-the-Art