A Flexible Neural Renderer for Material Visualization

Kt, Aakash; Sakurikar, Parikshit; Saini, Saurabh; Narayanan, P. J.

doi:10.1145/3355088.3365160

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some algorithms represent the visibility functions in vector form instead of sampled binary functions to render the direct illumination, e.g., Refs. [11,29,30]. Vectorized visibility [11] is a PRT algorithm, which precomputes the visibility for each vertex of a 3D model.…”

Section: Vectorized Visibilitymentioning

confidence: 99%

Temporal vectorized visibility for direct illumination of animated models

Wang,

Ho,

Xiao

et al. 2024

Comp. Visual Media

View full text Add to dashboard Cite

Direct illumination rendering is an important technique in computer graphics. Precomputed radiance transfer algorithms can provide high quality rendering results in real time, but they can only support rigid models. On the other hand, ray tracing algorithms are flexible and can gracefully handle animated models. With NVIDIA RTX and the AI denoiser, we can use ray tracing algorithms to render visually appealing results in real time. Visually appealing though, they can deviate from the actual one considerably. We propose a visibility-boundary edge oriented infinite triangle bounding volume hierarchy (BVH) traversal algorithm to dynamically generate visibility in vector form. Our algorithm utilizes the properties of visibility-boundary edges and infinite triangle BVH traversal to maximize the efficiency of the vector form visibility generation. A novel data structure, temporal vectorized visibility, is proposed, which allows visibility in vector form to be shared across time and further increases the generation efficiency. Our algorithm can efficiently render close-to-reference direct illumination results. With the similar processing time, it provides a visual quality improvement around 10 dB in terms of peak signal-to-noise ratio (PSNR) w.r.t. the ray tracing algorithm reservoir-based spatiotemporal importance resampling (ReSTIR).

show abstract

Section: Vectorized Visibilitymentioning

confidence: 99%

Temporal vectorized visibility for direct illumination of animated models

Wang,

Ho,

Xiao

et al. 2024

Comp. Visual Media

View full text Add to dashboard Cite

show abstract

“…Although proven powerful, more research in this field is needed in relation to a NN to comprehend the depth of objects for a 3D object reconstruction using convolutional architectures. Wu et al [ 42 ] already have demonstrated the possibilities of bridging the gap via the so-called 2.5D to generate shapes and forms, based on previous studies about the prediction of 3D shapes [ 43 , 44 , 45 , 46 ].…”

Section: Introductionmentioning

confidence: 99%

Color-Patterns to Architecture Conversion through Conditional Generative Adversarial Networks

Navarro-Mateu

Carrasco

Nieves³

2021

Biomimetics

View full text Add to dashboard Cite

Often an apparent complex reality can be extrapolated into certain patterns that in turn are evidenced in natural behaviors (whether biological, chemical or physical). The Architecture Design field has manifested these patterns as a conscious (inspired designs) or unconscious manner (emerging organizations). If such patterns exist and can be recognized, can we therefore use them as genotypic DNA? Can we be capable of generating a phenotypic architecture that is manifestly more complex than the original pattern? Recent developments in the field of Evo-Devo around gene regulators patterns or the explosive development of Machine Learning tools could be combined to set the basis for developing new, disruptive workflows for both design and analysis. This study will test the feasibility of using conditional Generative Adversarial Networks (cGANs) as a tool for coding architecture into color pattern-based images and translating them into 2D architectural representations. A series of scaled tests are performed to check the feasibility of the hypothesis. A second test assesses the flexibility of the trained neural networks against cases outside the database.

show abstract