Abstract Knitted fabrics present unique challenges for realistic rendering due to their complicated structure and scale‐dependent appearance. Existing methods typically rely on explicit yarn geometry, which is computationally complex, or texture‐based representations that require heavy storage and precomputed maps. In this paper, we introduce the first texture‐free, surface‐based appearance model for knitted fabrics, in which stitches are represented parametrically as thick curves and mapped directly onto fabric meshes. This avoids explicit yarn or fiber geometry, yet preserves the characteristic 3D look of yarn‐based models. Unlike prior surface‐based approaches, our method produces realistic volumetric effects such as depth, parallax, and silhouette preservation. To achieve this, we propose a curvature‐aware parallax mapping technique that ensures coherent appearance at grazing angles. Furthermore, we extend the appearance model to a multi‐scale formulation that aggregates geometry and visibility over texture footprints and adjusts roughness parameters for stable far‐field rendering. Our model combines the efficiency and simplicity of surface‐based methods with the volumetric realism of fiber‐based models, reproducing characteristic knit effects such as 3D stitch structure in a multi‐scale manner without the complexity or storage cost of texture‐based approaches.

Despite recent advances in text-to-image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that first produces a G-buffer (albedo, normals, depth, roughness, shading, and metallic) from a text prompt and then renders a final image through a PBR-inspired branch network. This intermediate representation enables fine-grained control: users can copy and paste within specific G-buffer channels to insert or reposition objects, or apply masks to the irradiance channel to adjust lighting locally. As a result, real objects can be seamlessly integrated into virtual scenes. By separating user-friendly scene description from image rendering, our method offers a practical balance between detailed post-generation control and efficient text-driven synthesis. We demonstrate its effectiveness through quantitative evaluations and a user study with 156 participants, showing consistent human preference over strong baselines and confirming that G-buffer control extends the flexibility of text-guided image generation.

We propose a complete pipeline for modeling and rendering realistic bird feathers from a single photograph, achieving both high visual fidelity and practical efficiency. Given a single input image of a feather, our approach extracts the feather's shaft curve, outline, and albedo, then reconstructs a compact hierarchical representation in a planar/curve (UV) domain. This representation encodes fine barb and barbule details procedurally, enabling continuous multiscale rendering with correct self-shadowing and masking. We analyze the appearance phenomena of different feathers and propose a new feather scattering model for non-iridescent feathers (e.g., parrot feathers), while introducing an additional sheen lobe to capture the distinctive fluffy rim-lighting effect. Our pipeline produces consistent, realistic results under arbitrary lighting and viewing conditions, and achieves real-time performance with a minimal memory footprint (0.02% of explicit-fiber geometry models), making it a practical solution for digital feather rendering without compromising realism.

Abstract Rendering woven fabrics is challenging due to the complex micro geometry and anisotropy appearance. Conventional solutions either fully model every yarn/ply/fibre for high fidelity at a high computational cost, or ignore details, that produce non‐realistic close‐up renderings. In this paper, we introduce a model that shares the advantages of both. Our model requires only binary patterns as input yet offers all the necessary micro‐level details by adding the yarn/ply/fibre implicitly. Moreover, we design a double‐layer representation to handle light transmission accurately and use a constant timed () approach to accurately and efficiently depict parallax and shadowing‐masking effects in a tandem way. We compare our model with curve‐based and surface‐based, on different patterns, under different lighting and evaluate with photographs to ensure capturing the aforementioned realistic effects.

Abstract Digital replication of woven fabrics presents significant challenges across a variety of sectors, from online retail to entertainment industries. To address this, we introduce an inverse rendering pipeline designed to estimate pattern, geometry, and appearance parameters of woven fabrics given a single close‐up image as input. Our work is capable of simultaneously optimizing both discrete and continuous parameters without manual interventions. It outputs a wide array of parameters, encompassing discrete elements like weave patterns, ply and fiber number, using Simulated Annealing. It also recovers continuous parameters such as reflection and transmission components, aligning them with the target appearance through differentiable rendering. For irregularities caused by deformation and flyaways, we use 2D Gaussians to approximate them as a post‐processing step. Our work does not pursue perfect matching of all fine details, it targets an automatic and end‐to‐end reconstruction pipeline that is robust to slight camera rotations and room light conditions within an acceptable time (15 minutes on CPU), unlike previous works which are either expensive, require manual intervention, assume given pattern, geometry or appearance, or strictly control camera and light conditions.

We introduce Reflectance Diffusion, a new neural text-to-texture model capable of generating high-fidelity SVBRDF maps from textual descriptions. Our method leverages a tandem neural approach, consisting of two modules, to accurately model the distribution of spatially varying reflectance as described by text prompts. Initially, we employ a pre-trained stable diffusion 2 model to generate a latent representation that informs the overall shape of the material and serves as our backbone model. Then, our ReflectanceUNet enables fine-tuning control over the material's physical appearance and generates SVBRDF maps. ReflectanceUNet module is trained on an extensive dataset comprising approximately 200,000 synthetic spatially varying materials. Our generative SVBRDF diffusion model allows for the synthesis of multiple SVBRDF estimates from a single textual input, offering users the possibility to choose the output that best aligns with their requirements. We illustrate our method's versatility by generating SVBRDF maps from a range of textual descriptions, both specific and broad. Our ReflectanceUNet model can integrate optional physical parameters, such as roughness and specularity, enhancing customization. When the backbone module is fixed, the ReflectanceUNet module refines the material, allowing direct edits to its physical attributes. Comparative evaluations demonstrate that ReflectanceFusion achieves better accuracy than existing text-to-material models, such as Text2Mat, while also providing the benefits of editable and relightable SVBRDF maps.

Measured Bidirectional Texture Function (BTF) can faithfully reproduce a realistic appearance but is costly to acquire and store due to its 6D nature (2D spatial and 4D angular). Therefore, it is practical and necessary for rendering to synthesize BTFs from a small example patch. While previous methods managed to produce plausible results, we find that they seldomly take into consideration the property of being dynamic, so a BTF must be synthesized before the rendering process, resulting in limited size, costly pre-generation and storage issues. In this paper, we propose a dynamic BTF synthesis scheme, where a BTF at any position only needs to be synthesized when being queried. Our insight is that, with the recent advances in neural dimension reduction methods, a BTF can be decomposed into disjoint low-dimensional components. We can perform dynamic synthesis only on the positional dimensions, and during rendering, recover the BTF by querying and combining these low-dimensional functions with the help of a lightweight Multilayer Perceptron (MLP). Consequently, we obtain a fully dynamic 6D BTF synthesis scheme that does not require any pre-generation, which enables efficient rendering of our infinitely large and non-repetitive BTFs on the fly. We demonstrate the effectiveness of our method through various types of BTFs taken from UBO2014 [Weinmann et al. 2014].

Abstract The realistic rendering of woven and knitted fabrics has posed significant challenges throughout many years. Previously, fiber‐based micro‐appearance models have achieved considerable success in attaining high levels of realism. However, rendering such models remains complex due to the intricate internal scatterings of hundreds of fibers within a yarn, requiring vast amounts of memory and time to render. In this paper, we introduce a new framework to capture aggregated appearance by tracing many light paths through the underlying fiber geometry. We then employ lightweight neural networks to accurately model the aggregated BSDF, which allows for the precise modeling of a diverse array of materials while offering substantial improvements in speed and reductions in memory. Furthermore, we introduce a novel importance sampling scheme to further speed up the rate of convergence. We validate the efficacy and versatility of our framework through comparisons with preceding fiber‐based shading models as well as the most recent yarn‐based model.

Abstract Differentiable rasterization changes the standard formulation of primitive rasterization — by enabling gradient flow from a pixel to its underlying triangles — using distribution functions in different stages of rendering, creating a “soft” version of the original rasterizer. However, choosing the optimal softening function that ensures the best performance and convergence to a desired goal requires trial and error. Previous work has analyzed and compared several combinations of softening. In this work, we take it a step further and, instead of making a combinatorial choice of softening operations, parameterize the continuous space of common softening operations. We study meta‐learning tunable softness functions over a set of inverse rendering tasks (2D and 3D shape, pose and occlusion) so it generalizes to new and unseen differentiable rendering tasks with optimal softness.

Abstract Neural reflectance models are capable of reproducing the spatially‐varying appearance of many real‐world materials at different scales. Unfortunately, existing techniques such as NeuMIP have difficulties handling materials with strong shadowing effects or detailed specular highlights. In this paper, we introduce a neural appearance model that offers a new level of accuracy. Central to our model is an inception‐based core network structure that captures material appearances at multiple scales using parallel‐operating kernels and ensures multi‐stage features through specialized convolution layers. Furthermore, we encode the inputs into frequency space, introduce a gradient‐based loss, and employ it adaptive to the progress of the learning phase. We demonstrate the effectiveness of our method using a variety of synthetic and real examples.

The demands of creating an immersive Virtual Reality (VR) experience often exceed the raw capabilities of graphics hardware. Perceptually-driven techniques can reduce rendering costs by directing effort away from features that do not significantly impact the overall user experience while maintaining a high level of quality where it matters most. One such approach is foveated rendering, which allows for a reduction in the quality of the image in the peripheral region of the field-of-view where lower visual acuity results in users being less able to resolve fine details. 6 Degrees of Freedom tracking allows for the exploration of VR environments through different modalities, such as user-generated head or body movements. The effect of self-induced motion on rendering optimization has generally been overlooked and is not yet well understood. To explore this, we used Variable Rate Shading (VRS) to create a foveated rendering method triggered by the translational velocity of the users and studied different levels of shading Level-of-Detail (LOD). We asked 10 participants in a within-subjects design to report whether they noticed a degradation in the rendering of a rich environment when performing active ego-movement or when being passively transported through the environment. We ran a psychophysical experiment using an accelerated stochastic approximation staircase method and modified the diameter and the LOD of the peripheral region. Our results show that self-induced walking can be used to significantly improve the savings of foveated rendering by allowing for an increased size of the low-quality area in a foveated algorithm compared to the passive condition. After fitting psychometric functions showcasing the percentage of correct responses related to different shading rates in the two types of movements, we also report the threshold severity (75%) point for when participants are able to detect such degradation. We argue such metrics can inform the future design of movement-dependent foveated techniques that could reduce computational load and increase energy savings.

Abstract Realistic cloth rendering is a longstanding challenge in computer graphics due to the intricate geometry and hierarchical structure of cloth: Fibers form plies which in turn are combined into yarns which then are woven or knitted into fabrics. Previous fiber‐based models have achieved high‐quality close‐up rendering, but they suffer from high computational cost, which limits their practicality. In this paper, we propose a novel hierarchical model that analytically aggregates light simulation on the fiber level by building on dual‐scattering theory. Based on this, we can perform an efficient simulation of ply and yarn shading. Compared to previous methods, our approach is faster and uses less memory while preserving a similar accuracy. We demonstrate both through comparison with existing fiber‐based shading models. Our yarn shading model can be applied to curves or surfaces, making it highly versatile for cloth shading. This duality paired with its simplicity and flexibility makes the model particularly useful for film and games production.

Micro-appearance models have brought unprecedented fidelity and details to cloth rendering. Yet, these models neglect fabric mechanics: when a piece of cloth interacts with the environment, its yarn and fiber arrangement usually changes in response to external contact and tension forces. Since subtle changes of a fabric's microstructures can greatly affect its macroscopic appearance, mechanics-driven appearance variation of fabrics has been a phenomenon that remains to be captured. We introduce a mechanics-aware model that adapts the microstructures of cloth yarns in a physics-based manner. Our technique works on two distinct physical scales: using physics-based simulations of individual yarns, we capture the rearrangement of yarn-level structures in response to external forces. These yarn structures are further enriched to obtain appearance-driving fiber-level details. The cross-scale enrichment is made practical through a new parameter fitting algorithm for simulation, an augmented procedural yarn model coupled with a custom-design regression neural network. We train the network using a dataset generated by joint simulations at both the yarn and the fiber levels. Through several examples, we demonstrate that our model is capable of synthesizing photorealistic cloth appearance in a mechanically plausible way.

Simulating the appearance of woven fabrics is challenging due to the complex interplay of lighting between the constituent yarns and fibers. Conventional surface-based models lack the fidelity and details for producing realistic close-up renderings. Micro-appearance models, on the other hand, can produce highly detailed renderings by depicting fabrics fiber-by-fiber, but become expensive when handling large pieces of clothing. Further, neither surface-based nor micro-appearance model has not been shown in practice to match measurements of complex anisotropic reflection and transmission simultaneously. In this paper, we introduce a practical appearance model for woven fabrics. We model the structure of a fabric at the ply level and simulate the local appearance of fibers making up each ply. Our model accounts for both reflection and transmission of light and is capable of matching physical measurements better than prior methods including fiber based techniques. Compared to existing micro-appearance models, our model is light-weight and scales to large pieces of clothing.

MOTIVATION: Measurements of gene expression over time enable the reconstruction of transcriptional networks. However, Bayesian networks and many other current reconstruction methods rely on assumptions that conflict with the differential equations that describe transcriptional kinetics. Practical approximations of kinetic models would enable inferring causal relationships between genes from expression data of microarray, tag-based and conventional platforms, but conclusions are sensitive to the assumptions made. RESULTS: The representation of a sufficiently large portion of genome enables computation of an upper bound on how much confidence one may place in influences between genes on the basis of expression data. Information about which genes encode transcription factors is not necessary but may be incorporated if available. The methodology is generalized to cover cases in which expression measurements are missing for many of the genes that might control the transcription of the genes of interest. The assumption that the gene expression level is roughly proportional to the rate of translation led to better empirical performance than did either the assumption that the gene expression level is roughly proportional to the protein level or the Bayesian model average of both assumptions. AVAILABILITY: http://www.oisb.ca points to R code implementing the methods (R Development Core Team 2004). SUPPLEMENTARY INFORMATION: http://www.davidbickel.com.