OpenHumanBRDF: Human Material Dataset

• OpenHumanBRDF is a full-body human dataset providing UV-aligned, high-quality material maps including displacement and subsurface scattering for enhanced realism.
• The dataset employs a controlled per-class material parameterization for four key dielectric materials, derived from 147 high-resolution 3D scans.
• It underpins the HumanMaterial framework by enabling progressive training with a fixed PBR model to alleviate ill-posedness in human material estimation.

Searching arXiv for the cited paper and topic to ground the article. arxiv_search({"^^^^^^^^2query2 OR OpenHumanBRDF OR \2^^^^^^^^"HumanMaterial: Human Material Estimation from a Single Image via Progressive Training\"", "max_results": 5, "sort_by": "submittedDate", "sort_order": "descending"}) Retrieving the arXiv record for the dataset-defining paper. arxiv_search({"^^^^^^^^2query2 "max_results": 3, "sort_by": "relevance", "sort_order": "descending"}) OpenHumanBRDF is a human-material dataset introduced in connection with full-body human inverse rendering based on physically-based rendering. It is described as a higher-quality dataset constructed from scanned real data and statistical material data, with the explicit goal of alleviating the ill-posedness that arises when material maps are weakly constrained by rendering supervision alone. In addition to normal, diffuse albedo, roughness, and specular albedo, it provides displacement and subsurface scattering, with the stated purpose of enhancing rendering realism, especially for skin. The dataset is presented together with the "HumanMaterial" framework, which uses it for single-image human material estimation (&&&^^^^2query2^^^^&&&).

^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^. Dataset scope and subject composition

OpenHumanBRDF contains ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^47 full-body human models acquired from RenderPeople, and these are described as all originally 3D scans (&&&^^^^2query2^^^^&&&). The subject pool is gender balanced (≈5^^^^2query2^^^^ % male, 5^^^^2query2^^^^ % female), spans six ethnicities evenly represented: Asian, Black, Indian, Middle Eastern, White, Hispanic/Latino (≈^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^6.7 % each), and covers an age range: ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^9–5^^^^2query2^^^^ (to maximize adult diversity).

The dataset assumes that the human body is composed of four principal dielectric materials, following Akenine-Möller et al. (RTR 2^^^^2query2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^8):

• Hair
• Skin
• Fabric (clothing)
• Leather (accessories such as belts, shoes)

Diversity is described along several axes: body shape, clothing style and material (fabric vs leather), hair style, and skin tone. Each subject is uniformly rendered under multiple camera views and environment maps to cover a broad space of appearance (&&&^^^^2query2^^^^&&&).

This construction places OpenHumanBRDF in a specific regime of human inverse rendering. It is not described as a generic material corpus spanning arbitrary object classes; rather, it is a controlled, full-body human dataset whose variability is organized around scanned geometry, UV-aligned maps, and four material classes.

2. Acquisition pipeline and material-map representation

The acquisition protocol begins with the high-resolution scanned meshes and UV layouts as provided by RenderPeople. In Blender (v2.8+), the pipeline assign[s] one of the four material classes to each mesh region, after which PBR parameters are set and six per-texel maps are baked via Blender’s Cycles/Eevee engines (&&&^^^^2query2^^^^&&&).

The six baked maps are:

• normal (tangent-space)
• diffuse albedo
• roughness
• specular albedo
• subsurface scattering weight
• displacement

For each UV texel PRESERVED_PLACEHOLDER_^^^^2query2^^^^, OpenHumanBRDF provides these maps in linear color space (32-bit float or ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^6-bit half float). Their semantics are specified as follows (&&&^^^^2query2^^^^&&&):

• Normal (3-channel): world→tangent-space normal, mapped to PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^
• Diffuse albedo (3-channel): linear RGB reflectance
• Roughness (^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^-channel): scalar $\in[0,1]$
• Specular albedo (^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^-channel): scalar $F_0 \in[0,1]$
• Subsurface scattering weight (^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^-channel): scalar $\mathrm{sss} \in[0,1]$, used in Disney’s “BSSRDF” approximation
• Displacement (^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^-channel): signed distance from the base mesh surface along the normal direction, in meters

The derivation procedure is also explicit. In Blender’s Shader Editor, each principled BSDF is assigned the fixed $F_0$, roughness, and $\mathrm{sss}$ values, and the outputs of each parameter node are baked directly to image textures. Displacement is baked via Blender’s Displacement modifier into a height map (&&&^^^^2query2^^^^&&&).

A central design feature is that all maps are baked to the subject’s UV space to ensure pixel-perfect alignment. This makes OpenHumanBRDF particularly suitable for supervised map regression, since appearance images, masks, and material parameters can be related through a stable UV parameterization rather than only through image-space correspondence.

3. Material parameterization and rendering model

The dataset uses a fixed per-class parameterization guided by RTR 2^^^^2query2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^8 statistical ranges. Each of the four material classes is assigned scalar values for $F_0$, roughness, and SSS weight (&&&^^^^2query2^^^^&&&).

Class	$F_0$	Roughness
Hair	^^^^2query2^^^^.239	^^^^2query2^^^^.5^^^^2query2
Skin	^^^^2query2^^^^.^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^84	^^^^2query2^^^^.4^^^^2query2
Fabric	^^^^2query2^^^^.263	^^^^2query2^^^^.85
Leather	^^^^2query2^^^^.224	^^^^2query2^^^^.25

Class	SSS weight
Hair	^^^^2query2^^^^.^^^^2query2query2
Skin	^^^^2query2^^^^.^^^^2query2
Fabric	^^^^2query2^^^^.^^^^2query2query2
Leather	^^^^2query2^^^^.^^^^2query2query2

The parameter meanings are specified directly: $F_0$ is the Fresnel reflectance at normal incidence (i.e. specular albedo), roughness controls the microfacet distribution spread, and SSS weight blends a simple approximate subsurface scattering term in Disney BSDF (&&&^^^^2query2^^^^&&&).

All appearance renders and render-loss supervision are based on a standard PBR shader with rendering equation

PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2query2^^^^

where PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^ is a surface point, PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \22^^^^ its normal, PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^3 the incident direction, PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^4 the exitant camera direction, and

PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^5

bundles the six material maps (&&&^^^^2query2^^^^&&&).

The BSDF is specified as Disney’s BSDF (Burley 2^^^^2query2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \22^^^^), described as a microfacet model with GGX normal distribution, Fresnel Schlick approximation, and an integrated subsurface term for skin. Its stated form is

PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^6

with PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^7 (&&&^^^^2query2^^^^&&&).

This rendering model is important because OpenHumanBRDF is not only a collection of textures; it is tied to a concrete forward model for synthesis and supervision. The inclusion of displacement and subsurface scattering distinguishes it from simpler human-material datasets that only expose normal, albedo, roughness, and specular terms.

4. Lighting, viewpoints, calibration, and splits

OpenHumanBRDF includes ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^ ^^^^2query2^^^^92 HDR environment maps (782 real from PolyHaven, 3^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2query2^^^^ synthetic) (&&&^^^^2query2^^^^&&&). For each subject, the camera is rotated on a fixed radius circle around the subject, and ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2query2query2^^^^ azimuthal angles are sampled evenly to produce ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2query2query2^^^^ views, corresponding to PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^8 increments.

For supervision generation, the pipeline renders the “appearance” (RGB) and all six material maps under two randomly selected environment maps. The split configuration is stated as follows (&&&^^^^2query2^^^^&&&):

• Training split: ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \22^^^^7 subjects → ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \22^^^^7 × ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2query2query2^^^^ = ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \22^^^^ 7^^^^2query2query2^^^^ data points
• Test split: 2^^^^2query2^^^^ subjects → 2^^^^2query2^^^^ × ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2query2^^^^ (single initial view) = 2^^^^2query2query2^^^^ data points

The statistical overview further specifies the sample contents:

• Train: ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \22^^^^7 subjects, ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \22^^^^ 7^^^^2query2query2^^^^ multi-view samples (each sample = RGB appearance + mask + 6 material maps + 2 env-relit appearances)
• Test: 2^^^^2query2^^^^ subjects, 2^^^^2query2query2^^^^ single-view samples

Calibration and consistency are handled uniformly. The same camera intrinsics and world-to-camera transform procedure is used for all renders, and the UV-baking process ensures alignment across maps and rendered appearances (&&&^^^^2query2^^^^&&&).

Preprocessing is also standardized. Each input appearance is accompanied by a foreground mask (from RemBG 2^^^^2query22query2^^^^ with optional alpha matting), and all maps are normalized to PRESERVED_PLACEHOLDER_^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^9 or $\in[0,1]$^^^^2query2^^^^ where appropriate and saved in linear space (no gamma) (&&&^^^^2query2^^^^&&&).

These design choices indicate that OpenHumanBRDF is intended for tightly controlled supervision. A plausible implication is that it supports both direct map estimation and render-based losses without requiring additional correspondence estimation between material maps and rendered observations.

5. Statistical structure and practical data organization

The dataset’s parameter distributions have a distinctive form. Because each material class has fixed roughness and specular values, the histograms of $\in[0,1]$^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^ and roughness exhibit four spikes at the class-specific settings. By contrast, diffuse albedos and normals are diverse due to per-subject color and geometry differences (&&&^^^^2query2^^^^&&&).

This point matters for interpreting the dataset correctly. A common misunderstanding would be to treat OpenHumanBRDF as a source of continuously varying human BRDF measurements. The summary instead specifies a hybrid construction: geometric and appearance diversity come from scanned subjects and varied rendering conditions, while some BRDF parameters are discretized by material class. This suggests that the dataset emphasizes robust human material estimation under structured priors rather than unconstrained recovery of arbitrary continuous reflectance fields.

The storage format is designed for high-precision rendering workflows. The provided file formats are (&&&^^^^2query2^^^^&&&):

• Appearance, mask, and baked maps: OpenEXR (.exr) or high-precision PNG (.png, ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^6-bit float) per channel
• Environment maps: HDR (.hdr) at 4 ^^^^2query2^^^^96×2 ^^^^2query2^^^^48 px
• Relit appearances: PNG/JPEG for quick preview, EXR for high precision

An example directory layout includes subjects.txt for split definitions, envs/ for the ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^ ^^^^2query2^^^^92 HDR maps, per-subject folders with appearance/, materials/, masks/, and relit/, and within materials/ the files normal.exr, albedo.exr, roughness.exr, specular.exr, sss_weight.exr, and displacement.exr (&&&^^^^2query2^^^^&&&). The example also lists relit/ as containing 5 novel-env relit images.

6. Role in HumanMaterial and methodological significance

OpenHumanBRDF is introduced in the paper together with HumanMaterial, a model for human material estimation from a single image via progressive training (&&&^^^^2query2^^^^&&&). The paper motivates the dataset by noting that inverse rendering requires estimating multiple material maps and usually relies on rendering constraints, but the absence of constraints on the material maps makes inverse rendering an ill-posed task. Previous approaches are described as using material datasets with simplified material data and rendering equation, leading to rendering results with limited realism, especially that of skin (&&&^^^^2query2^^^^&&&).

The stated contribution of OpenHumanBRDF within this framework is to provide stronger supervision through higher-quality material maps and a richer rendering model. Because the target space includes more maps, the paper argues that using an end-to-end model as in the previous work struggles to balance the importance among various material maps, and leads to model underfitting. HumanMaterial therefore first obtain[s] the initial material results via three prior models, and then refine[s] the results by a finetuning model. Since different maps have different significance for rendering results, the method introduces Controlled PBR Rendering (CPR) loss, which enhances the importance of the materials to be optimized during the training of prior models (&&&^^^^2query2^^^^&&&).

In this context, OpenHumanBRDF functions as more than a static asset repository. It supplies aligned map supervision, relighting supervision, and a fixed PBR forward model that can support staged optimization strategies. This suggests a close coupling between dataset design and training methodology: the dataset’s structured map decomposition directly informs the progressive training regime.

7. Interpretation, strengths, and limitations

The strongest stated properties of OpenHumanBRDF are its use of scanned real data, statistical material data, pixel-perfect UV alignment, multiple camera views, and HDR environment-map illumination, together with explicit support for displacement and subsurface scattering (&&&^^^^2query2^^^^&&&). These features make it well matched to full-body human inverse rendering pipelines that require both physically based supervision and map-level targets.

At the same time, the dataset summary makes several constraints explicit. The material taxonomy is restricted to four principal dielectric materials. The scalar parameters $\in[0,1]$2, roughness, and SSS weight are fixed per class rather than continuously sampled. The age range is ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^9–5^^^^2query2^^^^, and subject identities are limited to the ^^^^2id:(Jiang et al., 24 Jul 2025) OR OpenHumanBRDF OR \2^^^^47 full-body human models acquired from RenderPeople (&&&^^^^2query2^^^^&&&). None of these are defects in themselves, but they delimit the dataset’s scope.

Access is described prospectively rather than as an already completed release. The authors state that they plan to open-source the dataset on GitHub (link to be released upon paper acceptance) and that it will be distributed under a Creative-Commons (CC BY-SA) license to allow academic and noncommercial use (&&&^^^^2query2^^^^&&&).

Taken together, OpenHumanBRDF is best understood as a controlled, full-body human material dataset for inverse rendering under a Disney-style PBR model. Its main distinguishing property is not unconstrained reflectance diversity, but the combination of scanned human geometry, UV-aligned supervision, class-structured material parameterization, and rendering assets designed for relighting and material estimation.