1,720,990 research outputs found
Target-Aware Image Denoising for Inverse Monte Carlo Rendering
No full textPhysically based differentiable rendering allows an accurate light transport simulation to be differentiated with respect to the rendering input, i.e., scene parameters, and it enables inferring scene parameters from target images, e.g., photos or synthetic images, via an iterative optimization. However, this inverse Monte Carlo rendering inherits the fundamental problem of the Monte Carlo integration, i.e., noise, resulting in a slow optimization convergence. An appealing approach to addressing such noise is exploiting an image denoiser to improve optimization convergence. Unfortunately, the direct adoption of existing image denoisers designed for ordinary rendering scenarios can drive the optimization into undesirable local minima due to denoising bias. It motivates us to reformulate a new image denoiser specialized for inverse rendering. Unlike existing image denoisers, we conduct our denoising by considering the target images, i.e., specific information in inverse rendering. For our target-aware denoising, we determine our denoising weights via a linear regression technique using the target. We demonstrate that our denoiser enables inverse rendering optimization to infer scene parameters robustly through a diverse set of tests.
Adaptive Kernel Inference for Dense and Sharp Occupancy Grids
No full textIn this paper, we present a new approach, AKIMap, that uses an adaptive kernel inference for dense and sharp occupancy grid representations. Our approach is based on the multivariate kernel estimation, and we propose a simple, two-stage based method that selects an adaptive bandwidth matrix for an efficient and accurate occupancy estimation. To utilize correlations of occupancy observations given sparse and non-uniform distributions of point samples, we propose to use the covariance matrix as an initial bandwidth matrix, and then optimize the bandwidth matrix by adjusting its scale in an efficient, data-driven way for on-the-fly mapping. We demonstrate that the proposed technique estimates occupancy states more accurately than state-of-the-art methods given equal-data or equal-time settings, thanks to our adaptive inference. Furthermore, we show the practical benefits of the proposed work in on-the-fly mapping and observe that our adaptive approach shows the dense as well as sharp occupancy representations in a real environment
P-RPF: Pixel-Based Random Parameter Filtering for Monte Carlo Rendering
No full textIn this paper we propose Pixel-based Random Parameter Filtering (P-RPF) for efficiently denoising images generated from complex illuminations with a high sample count. We design various operations of our method to have time complexity that is independent from the number of samples per pixel. We compute feature weights by measuring the functional relationships between MC inputs and output in a sample basis. To accelerate this sample-basis process we propose to use an up sampling method for feature weights. We have applied our method to a wide variety of models with different rendering effects. Our method runs significantly faster than the original RPF, while maintaining visually pleasing and numerically similar results. As a result, our method shows more visually pleasing and numerically better results than RPF in an equal-time comparison
HCCMeshes
No full textRay tracing and collision detection are widely used for providing high-quality visualizations and user interactions. In these algorithms, we need to detect intersecting primitives between two input objects (e.g., a ray and a 3D object in ray tracing and two 3D objects in collision detection). In order to efficiently detect these intersecting primitives, hierarchical traversal and culling by using bounding volume hierarchies (BVHs) are commonly used
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
New Feature Generation for Denoising Gradient-Domain Rendering
No full textIn this thesis, we propose a new technique to utilize a feature-based denoiser in a gradient-domain rendering framework efficiently. The main idea of our method is to make a new feature using image gradients that originate from the gradient-domain rendering and put the generated feature into local regression based adaptive sampling and reconstruction method, which uses several rendering-specific features such as normal. The ultimate goal of this method is that some noise and artifacts can be additionally removed in the reconstructed image by making use of our generated feature with other rendering-specific features into the local regression based method. Moreover, for the purpose of robust estimation of our feature, we introduce a robust feature generation process including a weighted least squares (WLS) and bagging process.We demonstrate that our solution makes a quality improvement by linking the local regression based method into the gradient-domain rendering framework seamlessly.Maste
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Transformer-Convolution Hybrid U-Shape Neural Network for High-Quality Monte Carlo Denoising
No full textIn this thesis, we design a U-shape transformer-convolution hybrid neural network for the Monte Carlo denoising task. Our proposed model introduces additional convolutional blocks to the transformer-based network as a hybrid approach. The key motivation of this design is to continuously propagate, activate, and refine local detail information from the rendering features, using convolutional operations. A transformer
block and a convolution block in our proposed model form a transformer-convolution hybrid residual block. Additionally, our model adopts a U-shape transformer architecture to exploit inter-window dependencies with local window self-attention while reducing the computational cost. Thanks to these designs, our proposed denoiser can better utilize auxiliary features from Monte Carlo-rendered images, and outperforms state-of-the-art Monte Carlo denoisers for various test scenes, even with faster inference latency.Maste
- …
