Pursuing high-resolution 3D Geometry with Deep Learning

Yifan Wang
Yifan WangPhD Student at ETH Zurich
Pursuing high-resolution 3D
Geometry with Deep Learning
Yifan Wang
Motivation: rich geometry features
2
Genova et.al. CVPR 2020
Wang et.al. CVPR 2018
Park et.al. CVPR 2019
● Reality vs. Practicality
Outline
● Point upsampling
 [CVPR 2019]
● Differentiable Point Rendering
 [SIGGRAPH Asia 2019]
● Representation agnostic shape deformation
 [CVPR 2020]
3
Patch-based Progressive 3D Point Upsampling
Wang Yifan1, Shihao Wu1, Hui Huang2, Daniel Cohen-Or2,3, Olga Sorkine-Hornung1
1ETH Zurich, 2Shenzhen University, 3Tel Aviv University
Motivation / Objective
● Previous works cannot recover details.
● Goal: present fine-grained details even for high upsampling ratio
and sparse input using prior knowledge harnessed from external
data by a deep neural network.
input PU-Net (Yu et.al.)
Ground truth Ours
EAR (Huang et.al.)
16x upsampling
Key Idea
1. different levels of detail
2. progressive training [ProSR, CVPRW 2018]
3. adaptive receptive field
Key Idea
Iterative
4x+4x
(PU-Net)
input direct
16x
Key Idea
1. Tailor for different levels of detail with a sub-net
Iterative
4x+4x
(PU-Net)
input direct
16x
Key Idea
1. Tailor for different levels of detail with a sub-net
2. Train all levels of detail end-to-end in a progressive fashion.
Iterative
4x+4x
(PU-Net)
input direct
16x
Key Idea
1. Tailor for different levels of detail with a sub-net
2. Train all levels of detail end-to-end in a progressive fashion.
3. Reduce receptive field, i.e. large context for large-scale detail,
local context for fine-scale detail.
Iterative
4x+4x
(PU-Net)
input direct
16x
Key Idea
1. Tailor for different levels of detail with a sub-net
2. Train all levels of detail end-to-end in a progressive fashion.
3. Reduce receptive field, i.e. large context for large-scale detail,
local context for fine-scale detail.
Iterative
4x+4x
(PU-Net)
input direct
16x
ground
truth
Result
16x upsampling from 625 points.
Result
16x upsampling from 5000 points.
MPU applied to real scanned data.
Result
input denoised but
sparse
upsampled
MPU applied to real scanned data
(continued).
Result
sa2019.siggraph.org
Differentiable Surface Splatting for
Point-based Geometry Processing
Wang Yifan1, Felice Serena1, Shihao Wu1, Cengiz Öztireli2, Olga Sorkine-Hornung1
1ETH Zurich, 2Disney Research Zurich
Motivation: image-processing networks for 3D geometry
● Images-processing
networks can already
create stunning content
for 4K resolution.
[Vogel et.al. 2018]
Differentiable Rendering
Forward rendering
𝐼 = 𝑅 𝜃 ,
𝜃: camera, lighting,
material, geometry…
Inverse rendering
Δ𝐼 → Δ𝜃
𝝏𝑹/𝝏𝜽
image-based
neural
networks
Differentiable
Surface
Splatter (DSS)
Point cloud denoising via DSS
Point cloud denoising
input
output
Point cloud denoising
Input
RIMLS
[Öztireli et al. 2009]
EAR
[Huang et al. 2013] Ours
Point cloud denoising
Input Ours
RIMLS
[Öztireli et al. 2009]
EAR
[Huang et al. 2013]
Image-based point cloud filtering
L0-smoothing Super-pixel
Image-based point cloud filtering
We can apply image-filters directly to noisy inputs
Mesh-based
input filtered
Image-based point cloud deformation
initialization target
Neural Cages for
Detail-Preserving 3D Deformations
Wang Yifan Noam Aigerman Vladimir G. Kim
Siddhartha Chaudhuri Olga Sorkine-Hornung
Goal: detail preserving shape deformation
● Given two arbitrary shapes without correspondences, we can deform one to
match the other while preserving its rich geometric details.
# 27
source shape target shape deformed shape
Motivation: automatic design and character posing
design by deformation
# 28
character posing
Motivation: detail preservation
# 29
Groueix et.al. CGF 2019 Ours
source shape target shape
Motivation: detail preservation
# 30
detail preservation
(geometry regularizer)
+
Training Loss = shape alignment
(point-to-point distance)
● Shape alignment and detail preservation are two competing objectives.
Groueix et.al. CGF 2019
Source Target
Our key idea: dimension reduction using cages
● Constrain the input and output space, reduce the dimensionality of the
deformation space.
# 31
translation in the
reduced space
Interlude: Cage-based deformations
# 32
● Classic shape modeling
technique
● Coarse enclosing mesh
● Associated with the shape via
differentiable “cage
coordinates”
● Deformation by interpolation
Ju et.al. SIGGRAPH 2005
Joshi et.al. TOG 2007
Lipman et.al. TOG 2008
Our method: inference
# 33
CageNet
source shape
target shape
source cage
deformed cage
DeformNet
per cage-vertex offset
cage coordinates deformed shape
interpolation
interpolation
deformed shape
Our method: training
# 34
CageNet
source cage
deformed cage
DeformNet
per cage-vertex offset
skinning weights
shape alignment
(point-to-point distance)
deformed shape
feature preservation
(geometry regularizer)
source shape
target shape
skinning weights
cage rigidness
(penalize negative weights)
Advantage: efficiency and robustness
● Network complexity and computation is constant with respect to input shape
● Deformation quality is independent of sampling and local noise
# 35
deformed shape
120k vertices
target shape
CageNet
DeformNet
per cage-vertex
offset
1024 vertices
Application: stock amplification
Application: deformation transfer
# 37
training source
unseen targets
Application: deformation transfer
# 38
novel sources
unseen targets
Conclusion and future work
● A novel representation for
detail-preserving
deformations
● Other classic techniques
from interactive shape
modeling for various
applications and inputs
# 39
Jacobson et.al. SIGGRAPH 2011
Thank you
https://yifita.github.io
# 40
1 of 40

Recommended

ChatGPT and the Future of Work - Clark Boyd by
ChatGPT and the Future of Work - Clark Boyd ChatGPT and the Future of Work - Clark Boyd
ChatGPT and the Future of Work - Clark Boyd Clark Boyd
28K views69 slides
Getting into the tech field. what next by
Getting into the tech field. what next Getting into the tech field. what next
Getting into the tech field. what next Tessa Mero
6.6K views22 slides
Google's Just Not That Into You: Understanding Core Updates & Search Intent by
Google's Just Not That Into You: Understanding Core Updates & Search IntentGoogle's Just Not That Into You: Understanding Core Updates & Search Intent
Google's Just Not That Into You: Understanding Core Updates & Search IntentLily Ray
6.9K views99 slides
How to have difficult conversations by
How to have difficult conversations How to have difficult conversations
How to have difficult conversations Rajiv Jayarajah, MAppComm, ACC
5.6K views19 slides
Introduction to Data Science by
Introduction to Data ScienceIntroduction to Data Science
Introduction to Data ScienceChristy Abraham Joy
82.6K views51 slides
Time Management & Productivity - Best Practices by
Time Management & Productivity -  Best PracticesTime Management & Productivity -  Best Practices
Time Management & Productivity - Best PracticesVit Horky
169.8K views42 slides

More Related Content

Recently uploaded

Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT by
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITUpdates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITShapeBlue
206 views8 slides
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha... by
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...ShapeBlue
180 views18 slides
Generative AI: Shifting the AI Landscape by
Generative AI: Shifting the AI LandscapeGenerative AI: Shifting the AI Landscape
Generative AI: Shifting the AI LandscapeDeakin University
53 views55 slides
Kyo - Functional Scala 2023.pdf by
Kyo - Functional Scala 2023.pdfKyo - Functional Scala 2023.pdf
Kyo - Functional Scala 2023.pdfFlavio W. Brasil
457 views92 slides
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R... by
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...ShapeBlue
173 views15 slides
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue by
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlueCloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlueShapeBlue
138 views15 slides

Recently uploaded(20)

Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT by ShapeBlue
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBITUpdates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
Updates on the LINSTOR Driver for CloudStack - Rene Peinthor - LINBIT
ShapeBlue206 views
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha... by ShapeBlue
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...
Mitigating Common CloudStack Instance Deployment Failures - Jithin Raju - Sha...
ShapeBlue180 views
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R... by ShapeBlue
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
Setting Up Your First CloudStack Environment with Beginners Challenges - MD R...
ShapeBlue173 views
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue by ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlueCloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
CloudStack Object Storage - An Introduction - Vladimir Petrov - ShapeBlue
ShapeBlue138 views
The Role of Patterns in the Era of Large Language Models by Yunyao Li
The Role of Patterns in the Era of Large Language ModelsThe Role of Patterns in the Era of Large Language Models
The Role of Patterns in the Era of Large Language Models
Yunyao Li85 views
"Surviving highload with Node.js", Andrii Shumada by Fwdays
"Surviving highload with Node.js", Andrii Shumada "Surviving highload with Node.js", Andrii Shumada
"Surviving highload with Node.js", Andrii Shumada
Fwdays56 views
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ... by ShapeBlue
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...
Import Export Virtual Machine for KVM Hypervisor - Ayush Pandey - University ...
ShapeBlue119 views
NTGapps NTG LowCode Platform by Mustafa Kuğu
NTGapps NTG LowCode Platform NTGapps NTG LowCode Platform
NTGapps NTG LowCode Platform
Mustafa Kuğu423 views
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or... by ShapeBlue
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...
Zero to Cloud Hero: Crafting a Private Cloud from Scratch with XCP-ng, Xen Or...
ShapeBlue198 views
Initiating and Advancing Your Strategic GIS Governance Strategy by Safe Software
Initiating and Advancing Your Strategic GIS Governance StrategyInitiating and Advancing Your Strategic GIS Governance Strategy
Initiating and Advancing Your Strategic GIS Governance Strategy
Safe Software176 views
Digital Personal Data Protection (DPDP) Practical Approach For CISOs by Priyanka Aash
Digital Personal Data Protection (DPDP) Practical Approach For CISOsDigital Personal Data Protection (DPDP) Practical Approach For CISOs
Digital Personal Data Protection (DPDP) Practical Approach For CISOs
Priyanka Aash158 views
Declarative Kubernetes Cluster Deployment with Cloudstack and Cluster API - O... by ShapeBlue
Declarative Kubernetes Cluster Deployment with Cloudstack and Cluster API - O...Declarative Kubernetes Cluster Deployment with Cloudstack and Cluster API - O...
Declarative Kubernetes Cluster Deployment with Cloudstack and Cluster API - O...
ShapeBlue132 views
Why and How CloudStack at weSystems - Stephan Bienek - weSystems by ShapeBlue
Why and How CloudStack at weSystems - Stephan Bienek - weSystemsWhy and How CloudStack at weSystems - Stephan Bienek - weSystems
Why and How CloudStack at weSystems - Stephan Bienek - weSystems
ShapeBlue238 views
Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ... by ShapeBlue
Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ...Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ...
Backup and Disaster Recovery with CloudStack and StorPool - Workshop - Venko ...
ShapeBlue184 views
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas... by Bernd Ruecker
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
iSAQB Software Architecture Gathering 2023: How Process Orchestration Increas...
Bernd Ruecker54 views
Business Analyst Series 2023 - Week 4 Session 7 by DianaGray10
Business Analyst Series 2023 -  Week 4 Session 7Business Analyst Series 2023 -  Week 4 Session 7
Business Analyst Series 2023 - Week 4 Session 7
DianaGray10139 views
Enabling DPU Hardware Accelerators in XCP-ng Cloud Platform Environment - And... by ShapeBlue
Enabling DPU Hardware Accelerators in XCP-ng Cloud Platform Environment - And...Enabling DPU Hardware Accelerators in XCP-ng Cloud Platform Environment - And...
Enabling DPU Hardware Accelerators in XCP-ng Cloud Platform Environment - And...
ShapeBlue106 views

Featured

Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present... by
Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present...Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present...
Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present...Applitools
55.5K views138 slides
12 Ways to Increase Your Influence at Work by
12 Ways to Increase Your Influence at Work12 Ways to Increase Your Influence at Work
12 Ways to Increase Your Influence at WorkGetSmarter
401.7K views64 slides
ChatGPT webinar slides by
ChatGPT webinar slidesChatGPT webinar slides
ChatGPT webinar slidesAlireza Esmikhani
30.5K views36 slides
Ride the Storm: Navigating Through Unstable Periods / Katerina Rudko (Belka G... by
Ride the Storm: Navigating Through Unstable Periods / Katerina Rudko (Belka G...Ride the Storm: Navigating Through Unstable Periods / Katerina Rudko (Belka G...
Ride the Storm: Navigating Through Unstable Periods / Katerina Rudko (Belka G...DevGAMM Conference
3.6K views12 slides
Barbie - Brand Strategy Presentation by
Barbie - Brand Strategy PresentationBarbie - Brand Strategy Presentation
Barbie - Brand Strategy PresentationErica Santiago
25.1K views46 slides

Featured(20)

Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present... by Applitools
Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present...Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present...
Unlocking the Power of ChatGPT and AI in Testing - A Real-World Look, present...
Applitools55.5K views
12 Ways to Increase Your Influence at Work by GetSmarter
12 Ways to Increase Your Influence at Work12 Ways to Increase Your Influence at Work
12 Ways to Increase Your Influence at Work
GetSmarter401.7K views
Ride the Storm: Navigating Through Unstable Periods / Katerina Rudko (Belka G... by DevGAMM Conference
Ride the Storm: Navigating Through Unstable Periods / Katerina Rudko (Belka G...Ride the Storm: Navigating Through Unstable Periods / Katerina Rudko (Belka G...
Ride the Storm: Navigating Through Unstable Periods / Katerina Rudko (Belka G...
DevGAMM Conference3.6K views
Barbie - Brand Strategy Presentation by Erica Santiago
Barbie - Brand Strategy PresentationBarbie - Brand Strategy Presentation
Barbie - Brand Strategy Presentation
Erica Santiago25.1K views
Good Stuff Happens in 1:1 Meetings: Why you need them and how to do them well by Saba Software
Good Stuff Happens in 1:1 Meetings: Why you need them and how to do them wellGood Stuff Happens in 1:1 Meetings: Why you need them and how to do them well
Good Stuff Happens in 1:1 Meetings: Why you need them and how to do them well
Saba Software25.3K views
Introduction to C Programming Language by Simplilearn
Introduction to C Programming LanguageIntroduction to C Programming Language
Introduction to C Programming Language
Simplilearn8.5K views
The Pixar Way: 37 Quotes on Developing and Maintaining a Creative Company (fr... by Palo Alto Software
The Pixar Way: 37 Quotes on Developing and Maintaining a Creative Company (fr...The Pixar Way: 37 Quotes on Developing and Maintaining a Creative Company (fr...
The Pixar Way: 37 Quotes on Developing and Maintaining a Creative Company (fr...
Palo Alto Software88.4K views
9 Tips for a Work-free Vacation by Weekdone.com
9 Tips for a Work-free Vacation9 Tips for a Work-free Vacation
9 Tips for a Work-free Vacation
Weekdone.com7.2K views
How to Map Your Future by SlideShop.com
How to Map Your FutureHow to Map Your Future
How to Map Your Future
SlideShop.com275.1K views
Beyond Pride: Making Digital Marketing & SEO Authentically LGBTQ+ Inclusive -... by AccuraCast
Beyond Pride: Making Digital Marketing & SEO Authentically LGBTQ+ Inclusive -...Beyond Pride: Making Digital Marketing & SEO Authentically LGBTQ+ Inclusive -...
Beyond Pride: Making Digital Marketing & SEO Authentically LGBTQ+ Inclusive -...
AccuraCast3.4K views
Exploring ChatGPT for Effective Teaching and Learning.pptx by Stan Skrabut, Ed.D.
Exploring ChatGPT for Effective Teaching and Learning.pptxExploring ChatGPT for Effective Teaching and Learning.pptx
Exploring ChatGPT for Effective Teaching and Learning.pptx
Stan Skrabut, Ed.D.57.7K views
How to train your robot (with Deep Reinforcement Learning) by Lucas García, PhD
How to train your robot (with Deep Reinforcement Learning)How to train your robot (with Deep Reinforcement Learning)
How to train your robot (with Deep Reinforcement Learning)
Lucas García, PhD42.5K views
4 Strategies to Renew Your Career Passion by Daniel Goleman
4 Strategies to Renew Your Career Passion4 Strategies to Renew Your Career Passion
4 Strategies to Renew Your Career Passion
Daniel Goleman122K views
The Student's Guide to LinkedIn by LinkedIn
The Student's Guide to LinkedInThe Student's Guide to LinkedIn
The Student's Guide to LinkedIn
LinkedIn88.1K views
Different Roles in Machine Learning Career by Intellipaat
Different Roles in Machine Learning CareerDifferent Roles in Machine Learning Career
Different Roles in Machine Learning Career
Intellipaat12.4K views
Defining a Tech Project Vision in Eight Quick Steps pdf by TechSoup
Defining a Tech Project Vision in Eight Quick Steps pdfDefining a Tech Project Vision in Eight Quick Steps pdf
Defining a Tech Project Vision in Eight Quick Steps pdf
TechSoup 9.7K views

Pursuing high-resolution 3D Geometry with Deep Learning

Editor's Notes

  1. Hi, my name is Yifan, in the next 5 minutes I’ll being show you a cool new method for 3d shape deformation.
  2. Our lab is focusing on details
  3. Previous optimization-based methods focus on sharp features
  4. Tailor for different levels of detail with a sub-net Train all levels of detail end-to-end in a progressive fashion. Reduce receptive field, i.e. large context for large-scale detail, local context for fine-scale detail.
  5. The following slides visually demonstrate how each key idea contribute to better result. Shown here are the baseline
  6. Thanks for the introduction, today i'm going to talk about a differentiable renderer for point clouds.
  7. One motivation for our project is to leverage advanced neural image processing networks for classical point cloud processing tasks.
  8. As we should know by now, differentiable rendering aims at inferring the underlying scene parameters such as ... from the rendered images. It's typically used to update these scene parameters from the changes on image. The key is to define a gradient of the rendering function wrt the scene parameters.
  9. Use our DR to render images of the noisy point cloud, denoise the images with a state-of-the-art image denoising network, then use the denoised outputs as target images, propagate the change through the DR to the point cloud.
  10. The advantage compared to traditional denoising technique, is that many contemporary neural networks, such as generative adversarial networks, are able to hallucinate plausible details.
  11. Inspired by previous work, paparazzi, we can use DR to propagate image filtering to 3D models, in this case 3D point cloud.
  12. The advantage of our DR is that it’s very robust under noisy inputs compared mesh-based renderers.
  13. Lastly, as demonstrated before, our DR can also be used for image-based point cloud deformation, with large topology changes such as this one shown here.
  14. Hi, my name is Yifan, in the next 5 minutes I’ll being show you a cool new method for 3d shape deformation.
  15. The primary motivation of this work is detail preservation. More specifically, For example, the iron throne model is deformed to match an arbitrary sofa model, while keeping all the sword embellishment intact.
  16. This technique can be used in many areas such as for design and animation.
  17. First let me convince you that this is not a trivial task with a pair of simple chair models. We can see significant distortions in the deformation result generated by the state-of-the-art method.
  18. Secondly, shape alignment and feature preservation are in fact two competing if not conflicting objectives. As the example here shows, as we naively force the result to match the target and preserve the features in the source shape, the resulting geometry becomes a somewhat smudged version of the two.
  19. Our key idea is to improve the regularity of the deformation by reducing the dimensionality of the deformation space, we do so by representing the input and output with a much coarser mesh, called cage.
  20. This idea is inspired by the classic interactive shape modeling technique. Each of cage vertices is associated with the underlying shape using the so-called cage coordinates. Deformation is driven by offsetting the cage vertices. The deformed shape is obtained by interpolating cage vertices using the coordinates. While conventionally the cages are created by artists manually, i'll show you how we automatically create these cages for arbitrary input shapes.
  21. We use a neural network to automatically generate the enclosing cage conditioned on the source shape. From which, we can compute the coordinates deterministically. Then another network deforms this cage by offsetting cage vertices. Finally, we apply the interpolation to obtain the deformed shape. Because the interpolation is smooth by definition, the local geometry details can be preserved naturally.
  22. Our network can be trained using any shape alignment loss between the source and the target shape. We can control the rigidness of the cage via the skinning weights by penalizing negative values, (as these values leads to extrapolations instead of interpolation). Additional regularizers can be applied to improve the preservation of higher-level features, such as symmetry. Since the cage operations are fully differentiable, the entire network can be optimized end-to-end.
  23. Since the deformation is per cage-vertex, our network does not scale with the input resolution, thus can handle very complex shapes like this chair shown below. Furthermore, since the network needs to focus only on the global information, it’s robust to noisy and partial inputs.
  24. We can use our method to generate new variations of shapes, a practical tool for 3D stock amplification and design.
  25. As the cage deformation is not strictly tied to the enclosed shape, we can apply an existing deformation to a dissimilar source shape, a technique often referred to as “deformation transfer”. In this example, our network is trained to deform a human in rest pose to various other poses.
  26. we can then transform the predicted deformation to a new character, in this case a skeleton and a robot. This is achieved by optimizing the source cage for the new character. Compared to existing works, our method doesn’t require known correspondences with the target shape at inference time.
  27. To conclude, we proposed a novel representation for shape deformations that is detail preserving by construction. We envision that more classic interactive shape modeling techniques, such as cage-deformation used in this paper, can be incorporated into neural networks for different types of input and applications.
  28. To conclude, we proposed a novel representation for shape deformations that is detail preserving by construction. We envision that more classic interactive shape modeling techniques, such as cage-deformation used in this paper, can be incorporated into neural networks for different types of input and applications.