Alla sheffer. Alla SHEFFER Inventions, Patents and Patent Applications 2019-01-12

Alla sheffer Rating: 4,8/10 1631 reviews

Minchen Li

alla sheffer

At the heart of this process is the need to provide good correspondences between points on image contours and vertices on the model. They are especially powerful once annotated with semantic information such as salient regions and functional parts. We therefore transfer the exemplar style to the target via a sequence of element-level operations. The symmetry-aware factors are expressed as:. We use a unified utility function that explicitly models the time cost of human input across all steps of our method. We facilitate algorithmic synthesis of 3D models of man-made shapes which combines user-specified style, described via an exemplar shape, and functionality, encoded by a functionally different target shape. To simultaneously achieve scalability, diversity and style preservation, we define a valid solution space of arrangements that reflect the input style.

Next

Alla Sheffer's research works

alla sheffer

Based on an initial shape, the other shapes are then arranged in a circular chart with the selected shape in the center and similar shapes in the circles close to the center. We note that designers favor viewpoints that maximally reveal 3D shape information, and strategically sketch descriptive curves that convey intrinsic shape properties, such as curvature, symmetry, or parallelism. We then use the detected motion patterns to compute a per-triangle temporally adaptive reference shape and a stretch tensor based on it. The program, called FlowRep, was designed by computer science professor Alla Sheffer, in cooperation with Adobe Research and Washington University in St. Manually assembling such arrangements in virtual scenes is highly time consuming, especially when one needs to generate multiple diverse arrangements for numerous support surfaces and living spaces.


Next

Alla Sheffer's research works

alla sheffer

Sheffer is exploring the use of virtual and augmented reality interfaces for shape communication. To this end, we introduce a cross-structural element compatibility metric that estimates the impact of each operation on the edited shape. 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. When the user scrolls in any direction or changes the zoom level, the new cells of the grid that enter the screen space are dynamically filled with shapes based on the similarity graph. We train and validate our method on this dataset, showing it to successfully predict relative style similarity with near 90% accuracy based on 10-fold cross-validation. Abstract We present a new technique for image-based modeling using as in-put image contours and a deformable 3D template.

Next

Alla SHEFFER Inventions, Patents and Patent Applications

alla sheffer

The main challenge in performing cross-functional style transfer is to implicitly separate an object's style from its function: while stylistically the output shapes should be as close as possible to the exemplar, their original functionality and structure, as encoded by the target, should be strictly preserved. Since the current algorithm is best suited for human-made rather than natural shapes, Sheffer is also looking into improvements that will allow the system to produce top quality sketches of natural shapes. Our analysis is based on the notion of quartets, each defined by two pairs of shapes, where the shapes in each pair are close to each other, but far apart from the shapes in the other pair. This, however, does not reflect any special correspondence between the mesh geometry and the texture. Sheffer's program has worked well in user studies. True2Form is a sketch-based modeling system that reconstructs 3D curves from typical design sketches. The template models can be augmented to include properties such as bending stiffness and symmetry constraints.


Next

Alla SHEFFER Inventions, Patents and Patent Applications

alla sheffer

Instead of relying on quantitative distances, which may become unreliable between dissimilar shapes, we introduce a qualitative analysis which utilizes multiple distance measures but only in cases where the measures can be reliably compared. A calligram is an arrangement of words or letters that creates a visual image, and a compact calligram fits one word into a 2D shape. The input to our method is a wire sculpture design. Consequently, measuring scaled Jaco- bians is not a meaningful way to evaluate success of our algorithm, since we would mostly measure how much time we spent on tuning the input singularity graph. We validate our method via visual inspection, via comparison to artist created and ground truth surfaces, as well as comparison to prior art, and confirm that our results are well aligned with the computed flow fields and with viewer perception of the input networks. Recent literature point to the presence of similarly shaped, salient geometric elements as a main indicator of stylistic similarity between 3D shapes.

Next

Alla SHEFFER Inventions, Patents and Patent Applications

alla sheffer

An algorithmically computed style similarity measure that mimics human perception can benefit a range of computer graphics applications. As letter legibility is critical to the quality of compact calligrams, we conduct a large-scale crowd-sourced study on the impact of different letter deformations on legibility and use the results to train a letter legibility measure which guides the letter deformation. Matchmaker allows users to introduce scores of constraints while maintaining a valid one-to-one mapping between the embedding and the 3D surface. Our method leverages this exemplar to generate diverse arrangements reflecting the exemplar style for arbitrary furniture setups and layout dimensions. Her recent research applies insights about human perception and communication of shapes to algorithmic shape processing and has yielded novel modeling methods targeted at a broad user base. Deforming the input volumetric representation to provide the deformed object may be performed iteratively. To achieve this consistency we employ crowdsourcing to quantify the different components of our measure; we learn the relative perceptual importance of a range of elementary shape distances and other parameters used in our measurement from 50K responses to cross-structure style similarity queries provided by over 2500 participants.


Next

Alla Sheffer

alla sheffer

The content and layout of these arrangements reflect both context, e. We perceptually validate our approach by showing agreement between our algorithm and viewers in selecting applicable regularities. This proof leads to a set of angular constraints that must be satisfied for an immersion to exist in R-3. The sketches and 3D curves produced by the algorithm were deemed comparable to those produced by professional designers. We further demonstrate a compelling gallery of 3D character canvases created from a diverse set of cartoon drawings with matching 3D skeletons. Our method has three key elements: a path generation step which computes a global layout path suitable for embedding the input word; an alignment step to place the letters so as to achieve feature alignment between letter and shape protrusions while maintaining word legibility; and a final deformation step which deforms the letters to fit the shape while balancing fit against letter legibility. This is achieved by adding positional constraints to the planar parameterization.

Next

Alla SHEFFER Inventions, Patents and Patent Applications

alla sheffer

Our canvases serve as 3D geometric proxies for cartoon characters, enabling unconstrained 3D viewing, articulation, and non-photorealistic rendering. Artists routinely use gesture drawings to communicate ideated character poses for storyboarding and other digital media. During her time as a Full Professor at the University of British Columbia, she has helped make the Imager research group one of the strongest computer graphics research groups in the world. I was also very lucky to work with and on fluids simulation, and to work as an intern at with , , and. We first employ a graph-cut segmentation technique to extract spatially and temporally reliable surface motion patterns, detecting consistent compressing, stable, and stretching patches. Hons , Computer Science and Technology, , 2011 - 2015 I am a Ph.

Next

Minchen Li

alla sheffer

While a range of methods exist for discretizing 3D objects with an initial topologically suitable hex mesh, their output meshes frequently contain poorly shaped and even inverted elements, requiring a further quality optimization step. Large repositories of 3D shapes provide valuable input for data-driven analysis and modeling tools. Our solution combines classification into ground and non-ground with reconstruction of the continuous underlying surface. Extensive testing shows that the recovered surfaces agree very well with those reconstructed from manually corrected data. Balancing regularity enforcement against sketch fidelity at each step allows us to correct for inaccuracy inherent in free-hand sketching. The human perception of stylistic similarity transcends structure and function: for instance, a bed and a dresser may share a common style. The graph structure is obtained by triangulating the point clouds.


Next

I

alla sheffer

The usability of hexahedral meshes depends on the degree to which the shape of their elements deviates from a perfect cube; a single concave, or inverted element makes a mesh unusable. We present a method for organizing a heterogeneous collection of 3D shapes for overview and exploration. We introduce two new algorithms to perform the segmentation and to establish part correspondences that can also be used for many other applications in computer graphics. We then present a constrained optimization method that modifies input angles when they do not satisfy constraints. Moreover, although compression is predominant on our examples, dilatation still plays an important role, especially for the beret and puff sleeve examples where the natural shape needs to be inflated to account for the target. During subsequent posing of the 3D character models, they use these drawing as a reference, and perform the posing itself using 3D interfaces which require time and expert 3D knowledge to operate.

Next