-
公开(公告)号：WO2023090808A1
公开(公告)日：2023-05-25
申请号：PCT/KR2022/017969
申请日：2022-11-15
摘要： The present disclosure provides methods, apparatuses, and computer-readable mediums for representing shapes with probabilistic directed distance fields. In some embodiments, a method includes obtaining a camera representation and a latent shape vector representation of a scene. The camera representation indicates position information and direction information of a view of the scene. The method further includes calculating, based on the latent shape vector representation of the scene, a visibility score and a depth for each ray of a plurality of rays emanating from a corresponding plurality of positions and directions. The plurality of positions and directions are determined from the camera representation of the scene. The method further includes generating renders of geometric information of the scene using the visibility score and the depth of the plurality of rays.
-
公开(公告)号：WO2023044029A1
公开(公告)日：2023-03-23
申请号：PCT/US2022/043835
申请日：2022-09-16
申请人： NVIDIA CORPORATION
发明人： MUTHLER, Gregory , BURGESS, John , MORETON, Henry, Packard , URALSKY, Yury , OLIVER, Levi , ANDERSSON, Magnus , DELIGIANNIS, Johannes
摘要： Techniques applicable to a ray tracing hardware accelerator for traversing a hierarchical acceleration structure with reduced round-trip communications with a processor are disclosed. The reduction of round-trip communications with a processor during traversal is achieved by having a visibility mask that defines visibility states for regions within a geometric primitive available to be accessed in the ray tracing hardware accelerator when a ray intersection is detected for the geometric primitive.
-
公开(公告)号：WO2023043993A1
公开(公告)日：2023-03-23
申请号：PCT/US2022/043788
申请日：2022-09-16
申请人： NVIDIA CORPORATION
发明人： BURGESS, John , MUTHLER, Gregory , DIXIT, Nikhil , MORETON, Henry, Packard , URALSKY, Yury , ANDERSSON, Magnus , SALVI, Marco , KUBISCH, Christoph
摘要： A Displaced Micro-mesh (DMM) primitive enables high complexity geometry for ray and path tracing while minimizing the associated builder costs and preserving high efficiency. A structured, hierarchical representation implicitly encodes vertex positions of a triangle micro-mesh based on a barycentric grid, and enables microvertex displacements to be encoded efficiently (e.g., as scalars linearly interpolated between minimum and maximum triangle surfaces). The resulting displaced micro-mesh primitive provides a highly compressed representation of a potentially vast number of displaced microtriangles that can be stored in a small amount of space. Improvements in ray tracing hardware permit automatic processing of such primitive for ray-geometry intersection testing by ray tracing circuits without requiring intermediate reporting to a shader.
-
公开(公告)号：WO2022205627A1
公开(公告)日：2022-10-06
申请号：PCT/CN2021/100669
申请日：2021-06-17
申请人： 点昀技术(南通)有限公司
IPC分类号： G06T15/06
摘要： 一种端到端成像设备设计方法和装置，该方法包括：获取训练所述成像设备对应的预设场景（S110）；基于可微分的光线追踪引擎构建复杂透镜系统，并使用可微分的光线跟踪渲染方法并基于传感器模型仿真，获得预设场景对应的预处理图像（S120）；利用图像后处理网络，从所述预处理图像中恢复出所述预设场景对应的生成图像（S130）；根据所述生成图像和对应的参考图像，更新所述透镜的参数和图像后处理网络的参数（S140）。该方法实现了端到端计算成像，通过可微分的基于光线跟踪的光学引擎，在生成包含各种像差的模拟图像数据的同时，训练更新复杂光学透镜的参数，达到了用数据训练的方式进行成像设备设计的效果。
-
公开(公告)号：WO2022169378A1
公开(公告)日：2022-08-11
申请号：PCT/RU2021/000054
申请日：2021-02-08
摘要： The disclosure provides a traversal device (102, 202, 816) for real time incoherent ray tracing in a computing apparatus (100, 200). The incoherent rays are casted in a three-dimensional (3D) scene. The 3D scene includes objects ordered in a bounding volume hierarchy (BVH). The traversal device includes a plurality of traversal modules (104A-N, 204A-N, 300, 810A-N) for traversing the BVH. Each traversal module has a cache memory for storing nodes of the BVH in a compressed, low-bit form. The traversal device includes a plurality of triangle modules (106A-N, 206A-N, 400, 814A-N) for intersecting rays with triangles. Each triangle module has registers for storing a data of triangles in a compressed, low-bit form. Each traversal module is configured for checking ray-AABB intersections and each triangle module is configured for checking ray-triangle intersections by means of native low-bit integer arithmetic computations providing less than 0.01% of false negative intersections.
-
公开(公告)号：WO2022159684A1
公开(公告)日：2022-07-28
申请号：PCT/US2022/013289
申请日：2022-01-21
申请人： NVIDIA CORPORATION
摘要： One embodiment of a method rendering one or more graphics images includes tracing a ray cone through a three-dimensional (3D) graphics scene, generating a refracted ray cone based on the ray cone and a two-dimensional (2D) coordinate frame, and rendering a graphics image based on the refracted ray cone.
-
公开(公告)号：WO2022143922A1
公开(公告)日：2022-07-07
申请号：PCT/CN2021/143187
申请日：2021-12-30
发明人： LIU, Xiang , WAN, Jun
摘要： Systems and methods for image rendering are provided. The methods may include: rasterizing a primitive to determine rendering parameters of primitive pixel points representing the primitive in a target image; determining depth of volume data pixel points representing volume data in a preset region in the target image; and performing a physical rendering operation on the volume data to obtain the target image based on the depth of the volume data pixel points, color information of the volume data pixel points, and the rendering parameters, wherein the rendering parameters at least include depth of the primitive pixel points and color information of the primitive pixel points.
-
公开(公告)号：WO2022131531A1
公开(公告)日：2022-06-23
申请号：PCT/KR2021/015700
申请日：2021-11-02
申请人： 세종대학교산학협력단
发明人： 박우찬
摘要： 본 발명은 동적 장면에 대한 집중도 기반의 레이 트레이싱(Ray Tracing) 방법 및 장치에 관한 것으로, 상기 방법은 특정 장면을 제1 해상도로 렌더링 하여 제1 영상을 생성하는 과정에서 샘플링 픽셀마다 프라이머리 레이(primary ray)의 충돌 여부를 결정하는 단계; 및 상기 제1 영상을 상기 제1 해상도보다 더 높은 제2 해상도로 렌더링 하여 제2 영상을 생성하는 과정에서 상기 샘플링 픽셀들 사이에 존재하는 후보 픽셀들에 대해 주변 픽셀들의 충돌 빈도에 따른 적응적인 임계치 조정을 통해 선택적 렌더링을 반복적으로 수행하는 단계를 포함한다.
-
公开(公告)号：WO2022104635A1
公开(公告)日：2022-05-27
申请号：PCT/CN2020/130048
申请日：2020-11-19
发明人： DU, Bo , GRUBER, Andrew Evan , XU, Yongjun
摘要： The present disclosure relates to graphics processing. An apparatus of the present disclosure may determine visibility streams corresponding to a target and a set of bins into which the target is divided. The apparatus may select one of a first rendering mode or a second rendering mode for the target based on the first visibility stream and based on the set of second visibility streams. When the first rendering mode is select, the apparatus may configure each of the set of bins into a first subset associated with a first type of rendering pass or a second subset associated with a second type of rendering pass. The apparatus may then render the target based on the selected one of the first rendering mode or the second rendering mode and, if applicable, based on the first rendering pass type or the second rendering pass type.
-
公开(公告)号：WO2022063260A1
公开(公告)日：2022-03-31
申请号：PCT/CN2021/120584
申请日：2021-09-26
申请人： 华为云计算技术有限公司
IPC分类号： G06T15/06
摘要： 一种渲染方法及装置。该方法用于渲染应用，该应用包括至少一个模型，每个模型包括多个面片，该渲染方法在渲染该应用的当前帧的过程中，确定当前视平面中像素对应的目标面片，获取该应用的历史帧的渲染过程中获得的目标面片的历史渲染结果，根据所述目标面片的历史渲染结果，计算所述像素的当前渲染结果。该渲染方法通过复用历史渲染结果，计算当前渲染结果，有效的提升了光线追踪渲染的效率。
-
-
-
-
-
-
-
-
-
搜索结果
255 条记录 (耗时 0.024 秒)
