Sphere tracing: a geometric method for the antialiased ray tracing of implicit surfaces

By John C. Hart. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (2019, background): “Larger values of δ allow for fast ray-tracing since each sample gives information of safe step sizes [23].”
Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes (2021, methodology): “To render neural SDFs directly, ray-tracing can be done with a root-finding algorithm such as sphere tracing [17].”
Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations (2019, methodology): “Here, we take inspiration from the classic sphere tracing algorithm [67].”
Neural Unsigned Distance Fields for Implicit Function Learning (2020, background): “We show that a slight modification of the sphere tracing algorithm [32] is enough to render NDF images, see Figure 4.”
Advances in Neural Rendering (2021, methodology): “The search of surface intersection is typically based on some variant of the sphere tracing al-gorithm [Har96].”
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (2023, background): “Alternatively, one could directly render the depth image us-ing Ω online with sphere tracing [14]; however, we found this leads to less efficiency, especially when there is a large number of pose hypotheses to render in parallel.”
Compressed Voxel-Based Mapping Using Unsupervised Learning (2016, methodology): “speeding up image-alignment [1] and raycasting [2] operations as well a s collision detection [3], motion planning [4] and articulat edbody motion tracking [5].”
DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing (2019, methodology): “Our method is inspired by Sphere Tracing [13] designed for rendering SDF volumes, where rays are shot from the camera pinhole along the direction of each pixel to search for the surface level set according to the signed distance value.”
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance (2020, methodology): “SDF has two beneﬁts in our context: First, it allows an efﬁcient ray casting with the sphere tracing algorithm [12, 17]; and second, IGR enjoys implicit regularization favoring smooth and realistic surfaces.”