Browse State-of-the-Art › Inverse Rendering
Inverse Rendering
87 papers with code · 1 benchmark · 3 datasets archive 2025-07-28
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.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Stanford-ORB (7 rows) | Neural-PBIR | Neural-PBIR Reconstruction of Shape, Material, and Illumination | — | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Most implemented papers archive 2025-07-28
30 shown of 87 papers with code (271 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
21 Nov 2023 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)We encourage the model to learn an accurate decomposition by computing losses on the estimated shading as well as the albedo implied by the intrinsic model.
-
24 Nov 2021 2 repositories listedWe present an efficient method for joint optimization of topology, materials and lighting from multi-view image observations.
-
13 Oct 2021 2 repositories listedLike other neural renderers, our system takes as input calibrated camera images and a proxy geometry of the scene, in our case a point cloud.
-
16 Jun 2025 1 repository listed Syntology ran 6 of 14 samples · 8 unverified · 14 pointer-only (licence)Gaussian Splatting have demonstrated remarkable novel view synthesis performance at high rendering frame rates.
-
9 Apr 2025 1 repository listedMethods apply it to relighting by separating radiance into BRDF parameters and lighting, yet produce inferior relighting quality with artifacts and unnatural indirect illumination due to the limited capability of each…
-
24 Mar 2025 1 repository listedTo address this limitation, we propose the concept of learning a spatially and directionally aware importance sampler for the rendering equation to accurately and flexibly capture the unconstrained complexity of a…
-
15 Mar 2025 1 repository listedFinding a balance between artistic beauty and machine-generated imagery is always a difficult task.
-
30 Jan 2025 1 repository listedIn particular, we refine the mesh and locally condition the surface smoothness based on the estimated normal texture and mesh curvature.
-
7 Jan 2025 1 repository listedGiven an image, our method leverages neural networks to predict initial material properties.
-
12 Dec 2024 1 repository listedTo address this limitation, we present an inverse rendering (IR) model capable of jointly estimating scene geometry, materials, and illumination.
-
1 Nov 2024 1 repository listedThe second stage then calculates shadow for each area light and sums up to render the final image.
-
16 Oct 2024 1 repository listedOur framework could precisely estimate the light, materials and geometry with mesh without prior of light, materials and geometry in a unified framework.
-
20 Sep 2024 1 repository listedIntrinsic image decomposition aims to separate the surface reflectance and the effects from the illumination given a single photograph.
-
4 Sep 2024 1 repository listedModeling outdoor scenes for the synthetic 3D environment requires the recovery of reflectance/albedo information from raw images, which is an ill-posed problem due to the complicated unmodeled physics in this process (e.
-
PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularization13 Aug 2024 1 repository listedThis paper addresses the problem of inverse rendering from photometric images.
-
13 Aug 2024 1 repository listedIn this paper, we propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, SVBRDF, and 3D spatially-varying lighting.
-
30 Jul 2024 1 repository listedThe key idea is to perform object-centric voxelization to capture the 3D nature of the scene, which infers per-object occupancy probabilities at individual spatial locations.
-
28 Jul 2024 1 repository listedIn this work we design a Unified Voxelization framework for explicit learning of scene representations, dubbed UniVoxel, which allows for efficient modeling of the geometry, materials and illumination jointly, thereby…
-
8 Jul 2024 1 repository listed Syntology ran 25 of 25 samples · 0 unverifiedReconstructing high-fidelity hand models with intricate textures plays a crucial role in enhancing human-object interaction and advancing real-world applications.
-
25 Jun 2024 1 repository listedThis paper aims to quantify uncertainty for SVBRDF acquisition in multi-view captures.
-
2 Apr 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)Natural Light Uncalibrated Photometric Stereo (NaUPS) relieves the strict environment and light assumptions in classical Uncalibrated Photometric Stereo (UPS) methods.
-
17 Jan 2024 1 repository listedReconstructing an object from photos and placing it virtually in a new environment goes beyond the standard novel view synthesis task as the appearance of the object has to not only adapt to the novel viewpoint but also…
-
16 Jan 2024 1 repository listedExperiments demonstrate that, with the flexible input of single or sparse multi-view videos, we reconstruct personalized high-fidelity blendshapes.
-
8 Dec 2023 1 repository listedWe present IntrinsicAvatar, a novel approach to recovering the intrinsic properties of clothed human avatars including geometry, albedo, material, and environment lighting from only monocular videos.
-
8 Dec 2023 1 repository listed Syntology ran 6 of 10 samples · 4 unverified · 10 pointer-only (licence)Our method achieves state-of-the-art performance in both relighting and novel view synthesis tasks among the recently proposed inverse rendering methods while achieving real-time rendering.
-
28 Nov 2023 1 repository listedThe incorporation of our illumination prior is enabled by a novel `outside-in' method for computing differentiable sky visibility based on a neural directional distance function.
-
26 Nov 2023 1 repository listed Syntology ran 3 of 3 samples · 0 unverifiedWe propose GS-IR, a novel inverse rendering approach based on 3D Gaussian Splatting (GS) that leverages forward mapping volume rendering to achieve photorealistic novel view synthesis and relighting results.
-
21 Nov 2023 1 repository listedWe propose a novel inverse rendering method that enables the transformation of existing indoor panoramas with new indoor furniture layouts under natural illumination.
-
15 Nov 2023 1 repository listedTraining our model on a curated dataset of 1.
-
24 Oct 2023 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.
Syntology lines on 7 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections