The realm of 3D computer vision and graphics has experienced exponential growth recently, enabling the creation of realistic virtual environments and digital representations of real-world objects. ...Central to this progression are 3D reconstruction methods that facilitate the virtualization of shape, color, and surface details of real objects. Current methods predominantly employ neural scene representations, which despite their efficacy, grapple with limitations such as necessitating a high number of captured images and the complexity of transforming these representations into explicit geometric forms.
An alternative strategy that has gained traction is the deployment of methods such as physically-based differentiable rendering (PBDR) and inverse rendering. These approaches require fewer viewpoints, yield explicit format results, and ensure a smoother transition to other representation methods. To meaningfully assess the performance of different 3D reconstruction methods, it is imperative to utilize benchmark scenes for comparison.
Despite the existence of standard objects and scenes within the literature, there is a noticeable deficiency in real-world benchmark data that concurrently captures camera, illumination, and scene parameters — all critical to high-fidelity 3D reconstructions using PBDR and inverse rendering-based methods. In this research, we introduce a methodology for capturing real-world scenes as virtual scenes, integrating illumination parameters alongside camera and scene parameters to enhance the veracity of virtual representations. In addition, we introduce a set of ten real-world scenes, along with their virtual counterparts, designed as benchmarks. These benchmarks encompass a fundamental variety of geometric constructs, including convex, concave, plain, and mixed surfaces. Additionally, we demonstrate the 3D reconstruction results of state-of-the-art 3D reconstruction methods employing PBDR in real-world scenes, using both established methodologies and our proposed one.
•Recent advancements in computer vision and graphics enabled realistic virtual scenes.•Cutting-edge computer graphics techniques can model a given virtual environment.•The latest virtual scene optimization methods can be applied to real-world scenes.•Combining multiscale L1 loss with structural losses improves reconstruction accuracy.
Display omitted
While previous neural rendering methods have shown promising results in novel view synthesis, they still face difficulties when dealing with challenging street scenes. For instance, certain objects ...or content may only appear in a limited number of views, which can result in blurry synthesized images with significant artifacts. To address this critical issue, we propose a novel point-based neural rendering framework that facilitates a photo-realistic street simulation environment. Specifically, we introduce the Neural Street Scene Renderer (NSSR) to handle holes resulting from sparse point clouds. We also present a parallel attention module (PAM) and a multi-scale feature fusion and selection module (FFSM) to recalibrate features. Additionally, we use a point cloud filter and Gaussian noise points to remove outliers or floating points in the air and repair sparse point clouds. Our experimental results on four datasets demonstrate the effectiveness of our proposed approach in synthesizing photo-realistic street scenes.
Virtual view synthesis plays a vital role in the application of multi-view and free-viewpoint videos. Depth-image-based rendering (DIBR) is the most commonly used approach in view synthesis, and many ...DIBR algorithms have been proposed. However, how to evaluate the quality of DIBR-synthesized images and benchmark the DIBR algorithms are still very challenging, which may hinder the further development of the view synthesis technique. Hence, an effective quality metric for evaluating the distortions in view synthesis is urgently needed. With this motivation, this paper presents a quality index for view synthesis by simultaneously measuring local Instance DEgradation and global Appearance (IDEA). Due to the imperfection of rendering algorithms, local geometric distortions are easily introduced around instance contours, causing instance degradation, which is the dominant distortion in synthesized views. In this work, image instances are first detected and local instance degradation is measured based on discrete orthogonal moments. Meantime, we propose to measure the global appearance of synthesized images based on the superpixel representation. By integrating both local and global aspects of the distortions, a more accurate quality model is built for view synthesis. Extensive experiments and comparisons have demonstrated the superiority of the proposed method in evaluating the quality of DIBR-synthesized images and benchmarking the performance of view synthesis algorithms.
We present a Monte Carlo path tracing technique to sample extended next event estimation contributions in participating media: we consider one additional scattering vertex on the way to the next ...event, accounting for focused blur, resulting in visually interesting image features. Our technique is tailored to thin homogeneous media with strongly forward scattering phase functions, such as water or atmospheric haze. Previous methods put emphasis on sampling transmittances or geometric factors, and are either limited to isotropic scattering, or used tabulation or polynomial approximation to account for some specific phase functions. We will show how to jointly importance sample the product of an arbitrary phase function with analytic sampling in the solid angle domain and the two reciprocal squared distance terms of the adjacent edges of the transport path. The technique is fast and simple to implement in an existing rendering system. Our estimator is designed specifically for forward scattering, so the new technique has to be combined with other estimators to cover the backward scattering contributions.
We present a technique that leverages ray tracing hardware available in recent Nvidia RTX GPUs to solve a problem other than classical ray tracing. Specifically, we demonstrate how to use these units ...to accelerate the point location of general unstructured elements consisting of both planar and bilinear faces. This unstructured mesh point location problem has previously been challenging to accelerate on GPU architectures; yet, the performance of these queries is crucial to many unstructured volume rendering and compute applications. Starting with a CUDA reference method, we describe and evaluate three approaches that reformulate these point queries to incrementally map algorithmic complexity to these new hardware ray tracing units. Each variant replaces the simpler problem of point queries with a more complex one of ray queries. Initial variants exploit ray tracing cores for accelerated BVH traversal, and subsequent variants use ray-triangle intersections and per-face metadata to detect point-in-element intersections. Although these later variants are more algorithmically complex, they are significantly faster than the reference method thanks to hardware acceleration. Using our approach, we improve the performance of an unstructured volume renderer by up to <inline-formula><tex-math notation="LaTeX">4\times</tex-math> <mml:math><mml:mrow><mml:mn>4</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="morrical-ieq1-3042930.gif"/> </inline-formula> for tetrahedral meshes and up to <inline-formula><tex-math notation="LaTeX">15\times</tex-math> <mml:math><mml:mrow><mml:mn>15</mml:mn><mml:mo>×</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="morrical-ieq2-3042930.gif"/> </inline-formula> for general bilinear element meshes, matching, or out-performing state-of-the-art solutions while simultaneously improving on robustness and ease-of-implementation.
Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation. By inverting such renderer, one can think of a learning approach to infer 3D ...information from 2D images. However, standard graphics renderers involve a fundamental discretization step called rasterization, which prevents the rendering process to be differentiable, hence able to be learned. Unlike the state-of-the-art differentiable renderers, which only approximate the rendering gradient in the back propagation, we propose a truly differentiable rendering framework that is able to (1) directly render colorized mesh using differentiable functions and (2) back-propagate efficient supervision signals to mesh vertices and their attributes from various forms of image representations, including silhouette, shading and color images. The key to our framework is a novel formulation that views rendering as an aggregation function that fuses the probabilistic contributions of all mesh triangles with respect to the rendered pixels. Such formulation enables our framework to flow gradients to the occluded and far-range vertices, which cannot be achieved by the previous state-of-the-arts. We show that by using the proposed renderer, one can achieve significant improvement in 3D unsupervised single-view reconstruction both qualitatively and quantitatively. Experiments also demonstrate that our approach is able to handle the challenging tasks in image-based shape fitting, which remain nontrivial to existing differentiable renderers. Code is available at https://github.com/ShichenLiu/SoftRas.
Lifting freehand concept sketches into 3D Gryaditskaya, Yulia; Hähnlein, Felix; Liu, Chenxi ...
ACM transactions on graphics,
11/2020, Volume:
39, Issue:
6
Journal Article
Peer reviewed
Open access
We present the first algorithm capable of automatically lifting real-world, vector-format, industrial design sketches into 3D. Targeting real-world sketches raises numerous challenges due to ...inaccuracies, use of overdrawn strokes, and construction lines. In particular, while construction lines convey important 3D information, they add significant clutter and introduce multiple accidental 2D intersections. Our algorithm exploits the geometric cues provided by the construction lines and lifts them to 3D by computing their intended 3D intersections and depths. Once lifted to 3D, these lines provide valuable geometric constraints that we leverage to infer the 3D shape of other artist drawn strokes. The core challenge we address is inferring the 3D connectivity of construction and other lines from their 2D projections by separating 2D intersections into 3D intersections and accidental occlusions. We efficiently address this complex combinatorial problem using a dedicated search algorithm that leverages observations about designer drawing pREFERENCES, and uses those to explore only the most likely solutions of the 3D intersection detection problem. We demonstrate that our separator outputs are of comparable quality to human annotations, and that the 3D structures we recover enable a range of design editing and visualization applications, including novel view synthesis and 3D-aware scaling of the depicted shape.
Micro-appearance models offer state-of-the-art quality for cloth renderings. Unfortunately, they usually rely on 3D volumes or fiber meshes that are not only data-intensive but also expensive to ...render. Traditional surface-based models, on the other hand, are light-weight and fast to render but normally lack the fidelity and details important for design and prototyping applications. We introduce a multi-scale, hybrid model to bridge this gap for thin fabrics. Our model enjoys both the compactness and speedy rendering offered by traditional surface-based models and the rich details provided by the micro-appearance models. Further, we propose a new algorithm to convert state-of-the-art micro-appearance models into our representation while qualitatively preserving the detailed appearance. We demonstrate the effectiveness of our technique by integrating it into a real-time rendering system.