Suzuran Takikawa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Suzuran Takikawa has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Alla Sheffer
The University of British Columbia, Vancouver, Canada
4 shared publications - Nicholas Vining
NVIDIA, Kitchener, Canada and The University of British Columbia, Kitchener, Canada
3 shared publications - Jinfan Yang
University of British Columbia, Vancouver, Canada
2 shared publications - Leo Foord-Kelcey
The University of British Columbia, Vancouver, Canada
2 shared publications - Congyi Zhang
The University of Hong Kong
1 shared publication - Curtis Andrus
Netflix Animation Studios, Vancouver, Canada
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
ADS: Random Sampling of Occupancy Functions using Adaptive Delaunay Scaffolding
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessADS: Random Sampling of Occupancy Functions using Adaptive Delaunay Scaffolding
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Capturing Non-Linear Human Perspective in Line Drawings
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessCapturing Non-Linear Human Perspective in Line Drawings
- Open Access
- 4 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (5) , 1-23
NESI: Neural Explicit-Shape-Intersection-Based Geometry Representation
Compressed representations of 3D shapes that are compact, accurate, and can be processed efficiently directly in compressed form, are extremely useful for digital media applications. Recent approaches in this space focus on learned implicit or parametric representations. While implicits are well suited for tasks such as in-out queries, they lack natural 2D parameterization, complicating tasks such as texture or normal mapping. Conversely, parametric representations support the latter tasks but are ill-suited for occupancy queries. We propose a novel learned alternative to these approaches, based on intersections of localized explicit , or height-field , surfaces. Since explicits can be trivially expressed both implicitly and parametrically, NESI directly supports a wider range of processing operations than implicit alternatives, including occupancy queries and parametric access. We represent input shapes using a collection of differently oriented height-field bounded half-spaces combined using volumetric Boolean intersections. We first tightly bound each input using a pair of oppositely oriented height-fields, forming a Double Height-Field (DHF) Hull . We refine this hull by intersecting it with additional localized height-fields (HFs) that capture surface regions in its interior. We minimize the number of HFs necessary to accurately capture each input and compactly encode both the DHF hull and the local HFs as neural functions defined over subdomains of \(\mathbb {R}^2\) . This reduced dimensionality encoding delivers high-quality compact approximations. Given similar parameter count, or storage capacity, NESI significantly reduces approximation error compared to the state-of-the-art, especially at lower parameter counts.- 4 July 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 44 (5) , 1-23
Open AccessNESI: Neural Explicit-Shape-Intersection-Based Geometry Representation
Compressed representations of 3D shapes that are compact, accurate, and can be processed efficiently directly in compressed form, are extremely useful for digital media applications. Recent approaches in this space focus on learned implicit or parametric representations. While implicits are well suited for tasks such as in-out queries, they lack natural 2D parameterization, complicating tasks such as texture or normal mapping. Conversely, parametric representations support the latter tasks but are ill-suited for occupancy queries. We propose a novel learned alternative to these approaches, based on intersections of localized explicit , or height-field , surfaces. Since explicits can be trivially expressed both implicitly and parametrically, NESI directly supports a wider range of processing operations than implicit alternatives, including occupancy queries and parametric access. We represent input shapes using a collection of differently oriented height-field bounded half-spaces combined using volumetric Boolean intersections. We first tightly bound each input using a pair of oppositely oriented height-fields, forming a Double Height-Field (DHF) Hull . We refine this hull by intersecting it with additional localized height-fields (HFs) that capture surface regions in its interior. We minimize the number of HFs necessary to accurately capture each input and compactly encode both the DHF hull and the local HFs as neural functions defined over subdomains of \(\mathbb {R}^2\) . This reduced dimensionality encoding delivers high-quality compact approximations. Given similar parameter count, or storage capacity, NESI significantly reduces approximation error compared to the state-of-the-art, especially at lower parameter counts. - Open Access
- 26 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Controllable Modular Trees
Trees are a ubiquitous part of virtual environments, but faithfully modeling trees is challenging because of their incredible diversity. Tree modeling methods face two key challenges, as users want to create trees that look realistic but retain control over key elements of their appearance, such as the shape of the tree crowns. Traditional tree modeling methods are geared to produce tree models that are both detailed and unique and are typically stored as high-triangle count meshes or skeletons plus radii. Storing and manipulating such traditional tree models comes with a significant memory cost. Recent approaches have proposed to use modular trees consisting of a finite set of branch modules, which are transformed (scaled, translated, and rotated) to jointly form realistic looking trees. Consequently, modular trees require orders of magnitude less memory than their traditional counterparts. However, existing methods for modeling modular trees focus on visual realism and provide only minimal mechanisms for artists to control the look and shape of the resulting trees. We propose a controllable method for modeling modular trees, enabling artists to define the tree’s overall crown shape while maintaining a plausible appearance using a small set of replicated branch modules. We formulate the computation of realistic modular trees that conform to a user-specified crown shape as a constrained mixed-variable optimization problem. We then compute the trees that satisfy these constraints using a method that grows trees one layer of branches at a time, maintaining realism throughout and promoting accurate approximation of the target crown shape. We extensively test our method on diverse crown shapes and compare against baselines, demonstrating its effectiveness.
- 26 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessControllable Modular Trees
Trees are a ubiquitous part of virtual environments, but faithfully modeling trees is challenging because of their incredible diversity. Tree modeling methods face two key challenges, as users want to create trees that look realistic but retain control over key elements of their appearance, such as the shape of the tree crowns. Traditional tree modeling methods are geared to produce tree models that are both detailed and unique and are typically stored as high-triangle count meshes or skeletons plus radii. Storing and manipulating such traditional tree models comes with a significant memory cost. Recent approaches have proposed to use modular trees consisting of a finite set of branch modules, which are transformed (scaled, translated, and rotated) to jointly form realistic looking trees. Consequently, modular trees require orders of magnitude less memory than their traditional counterparts. However, existing methods for modeling modular trees focus on visual realism and provide only minimal mechanisms for artists to control the look and shape of the resulting trees. We propose a controllable method for modeling modular trees, enabling artists to define the tree’s overall crown shape while maintaining a plausible appearance using a small set of replicated branch modules. We formulate the computation of realistic modular trees that conform to a user-specified crown shape as a constrained mixed-variable optimization problem. We then compute the trees that satisfy these constraints using a method that grows trees one layer of branches at a time, maintaining realism throughout and promoting accurate approximation of the target crown shape. We extensively test our method on diverse crown shapes and compare against baselines, demonstrating its effectiveness.