Near-exhaustive precomputation of secondary cloth effects

Kim, Doyub; Koh, Woojong; Narain, Rahul; Fatahalian, Kayvon; Treuille, Adrien; O’Brien, James F.

doi:10.1145/2461912.2462020

Cited by 81 publications

(58 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kim et al . [KKN*13] performed a near‐exhaustive precomputation of the state of a cloth throughout the motion of a character. At run‐time a secondary motion graph was explored to find the closest cloth state for the current pose.…”

Section: Related Workmentioning

confidence: 99%

Learning‐Based Animation of Clothing for Virtual Try‐On

Santesteban

Otaduy

Casas

2019

Computer Graphics Forum

166

225

View full text Add to dashboard Cite

This paper presents a learning‐based clothing animation method for highly efficient virtual try‐on simulation. Given a garment, we preprocess a rich database of physically‐based dressed character simulations, for multiple body shapes and animations. Then, using this database, we train a learning‐based model of cloth drape and wrinkles, as a function of body shape and dynamics. We propose a model that separates global garment fit, due to body shape, from local garment wrinkles, due to both pose dynamics and body shape. We use a recurrent neural network to regress garment wrinkles, and we achieve highly plausible nonlinear effects, in contrast to the blending artifacts suffered by previous methods. At runtime, dynamic virtual try‐on animations are produced in just a few milliseconds for garments with thousands of triangles. We show qualitative and quantitative analysis of results.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning‐Based Animation of Clothing for Virtual Try‐On

Santesteban

Otaduy

Casas

2019

Computer Graphics Forum

166

225

View full text Add to dashboard Cite

show abstract

“…On the other hand, pure data driven simulation methods such as [Guan et al 2012;Kavan et al 2011;de Aguiar et al 2009] circumvent the need for physical simulation (almost) completely by learning from real world data. As just recently shown by Kim et al [2013], successfully learning complex deformations from data is possible but requires a dauntingly huge amount of well structured training data which is often not available, in particular for captured data. A decomposition method that is able to build a latent deformation space that generalizes beyond the training data and allows for user input, as offered by our method, can help to overcome this limitation in the future.…”

Section: Facial Animation and Editingmentioning

confidence: 99%

Sparse localized deformation components

et al. 2013

View full text Add to dashboard Cite

Figure 1: Our method automatically decomposes any mesh animations like performance captured faces (left) or muscle deformations (right) into sparse and localized deformation modes (shown in blue). Left: a new facial expression is generated by summing deformation components. Our method automatically separates spatially confined effects like separate eyebrow motions from the data. Right: Our algorithm extracts individual muscle and bone deformations. The deformation components can then be used for convenient editing of the captured animation. Here, the deformation component of the clavicle is over-exaggerated to achieve an artistically desired look. AbstractWe propose a method that extracts sparse and spatially localized deformation modes from an animated mesh sequence. To this end, we propose a new way to extend the theory of sparse matrix decompositions to 3D mesh sequence processing, and further contribute with an automatic way to ensure spatial locality of the decomposition in a new optimization framework. The extracted dimensions often have an intuitive and clear interpretable meaning. Our method optionally accepts user-constraints to guide the process of discovering the underlying latent deformation space. The capabilities of our efficient, versatile, and easy-to-implement method are extensively demonstrated on a variety of data sets and application contexts. We demonstrate its power for user friendly intuitive editing of captured mesh animations, such as faces, full body motion, cloth animations, and muscle deformations. We further show its benefit for statistical geometry processing and biomechanically meaningful animation editing. It is further shown qualitatively and quantitatively that our method outperforms other unsupervised decomposition methods and other animation parameterization approaches in the above use cases.

show abstract

“…Guan et al [2012] combine a database of simulated fine garments with a parametrization of the underlying physical body to generate visually appealing results. Kim et al [2013] use a novel compression scheme to make the traversal of over 33 gigabytes of cloth training data tractable in real time. Zurdo et al [2013] compute a physical simulation on highresolution meshes offline and simplify it to a coarser mesh in real time.…”

Section: Data-driven Approachesmentioning

confidence: 99%

Real-time dynamic wrinkling of coarse animated cloth

Gillette

Peters

Vining

et al. 2015

Proceedings of the 14th ACM SIGGRAPH / Eurographics Symposium on Computer Animation

View full text Add to dashboard Cite

Figure 1: Coarse game-level cloth animation augmented with realistic looking wrinkles in real-time. AbstractDynamic folds and wrinkles are an important visual cue for creating believably dressed characters in virtual environments. Adding these fine details to real-time cloth visualization is challenging, as the low-quality cloth used for real-time applications often has no reference shape, an extremely low triangle count, and poor temporal and spatial coherence. We introduce a novel real-time method for adding dynamic, believable wrinkles to such coarse cloth animation. We trace spatially and temporally coherent wrinkle paths, overcoming the inaccuracies and noise in low-end cloth animation, by employing a two stage stretch tensor estimation process. We first employ a graph-cut segmentation technique to extract spatially and temporally reliable surface motion patterns, detecting consistent compressing, stable, and stretching patches. We then use the detected motion patterns to compute a per-triangle temporally adaptive reference shape and a stretch tensor based on it. We use this tensor to dynamically generate new wrinkle geometry on the coarse cloth mesh by taking advantage of the GPU tessellation unit. Our algorithm produces plausible fine wrinkles on real-world data sets at real-time frame rates, and is suitable for the current generation of consoles and PC graphics cards.

show abstract

Near-exhaustive precomputation of secondary cloth effects

Cited by 81 publications

References 41 publications

Learning‐Based Animation of Clothing for Virtual Try‐On

Learning‐Based Animation of Clothing for Virtual Try‐On

Sparse localized deformation components

Real-time dynamic wrinkling of coarse animated cloth

Contact Info

Product

Resources

About