Technical Videos

Topology Aware Vector Field Denoising

Authors: Renata Nascimento (D. Math/PUC-Rio), João Paixão (D. Math/PUC-Rio), Hélio Lopes (D. Math/PUC-Rio), Thomas Lewiner (D. Math/PUC-Rio).

Abstract: Recent developments in data acquisition technology enable to directly capture real vector fields, helping for a better understanding of physical phenomena. However measured data is corrupted by noise, puzzling the understanding of the phenomena. This turns the task of removing noise, i.e. denoising, an essential preprocessing step for a better analysis of the data. Nonetheless a careful use of denoising is required since usual algorithms not only remove the noise but can also eliminate information, in particular the vector field singularities, which are fundamental features in the analysis. This paper proposes a semi-automatic vector field denoising methodology, where the user visually controls the topological changes caused by classical vector field filtering in scale-spaces.

Length: 2 min 23 sec

Tuning Manifold Harmonics Filters

Authors: Thomas Lewiner (D. Math/PUC-Rio), Thales Vieira (I. Math/UFAL), Alex Bordignon (D. Math/PUC-Rio), Allyson Cabral (D. Math/PUC-Rio), Clarissa Marques (D. Math/PUC-Rio), João Paixão (D. Math/PUC-Rio), Lis Custódio (D. Math/PUC-Rio), Marcos Lage (D. Math/PUC-Rio), Maria Andrade (D. Math/PUC-Rio), Renata Nascimento (D. Math/PUC-Rio), Scarlett de Botton (D. Math/PUC-Rio), Sinésio Pesco (D. Math/PUC-Rio), Hélio Lopes (D. Math/PUC-Rio), Vinícius Mello (I. Math/UFBA), Adelailson Peixoto (I. Math/UFAL), Dimas Martinez (I. Math/UFAL).

Abstract: There are several techniques for automatic music visualization, which are included with virtually any media player. The basic ingredient of those techniques is spectral analysis of the sound, used to automatically generate parameters for procedural image generation. However, only a few music visualizations rely on 3d models. This paper proposes to use spectral mesh processing techniques, namely manifold harmonics, to produce 3d music visualization. The images are generated from 3d models by deforming an initial shape, mapping the sound frequencies to the mesh harmonics. A concise representation of such frequency mapping is proposed to permit for an animated gallery interface with genetic reproduction. Such galleries allow the user to quickly navigate between visual effects. %and eventually select and fine-tune his preferred one. Rendering such animated galleries in real-time is a challenging task, since it requires computing and rendering the deformed shapes at a very high rate. This paper introduces a direct GPU implementation of manifold harmonics filters, which allows to display animated gallery.

Length: 5 min 56 sec


Authors: Luiz Velho Director (Visgraf/IMPA), Leonardo Carvalho (Visgraf/IMPA), Fernanda Groetaers (Visgraf/IMPA).

Abstract: TuioSketch is a sketch-based modeling system that makes use of tangible interfaces with multi-touch interaction. It allows us to create tridimensional organic forms in a much more intuitive way than traditional modeling systems. In this video we show briefly how to create forms in TuioSketch using a multitouch device (the i.Table). Moreover, we explain the construction of the triangular mesh, which is one of the most significant contributions in this project.

Length: 2 min 57 sec

NETRA: Interactive Display for Estimating Refractive Errors and Focal Range

Authors: Vitor Fernando Pamplona (Instituto de Informática/UFRGS), Ankit Mohan (MIT Media Lab), Manuel M. Olveira Neto (Instituto de Informática/ UFRGS), Ramesh Raskar (MIT Media Lab).

Abstract: We introduce an interactive, portable, and inexpensive solution for estimating refractive errors in the human eye. While expensive optical devices for automatic estimation of refractive correction exist, our goal is to greatly simplify the mechanism by putting the human subject in the loop. Our solution is based on a high-resolution programmable display and combines inexpensive optical elements, interactive GUI, and computational reconstruction. The key idea is to interface a lenticular view-dependent display with the human eye at close range – a few millimeters apart. Via this platform, we create a new range of interactivity that is extremely sensitive to parameters of the human eye, such as the refractive errors, focal range, focusing speed, lens opacity, etc. We propose several simple optical setups, verify their accuracy, precision, and validate them in a user study.

Length: 3 min

Real Videos with Artificial Rain

Authors: Bruno Barcellos S. Coutinho (COPPE/UFRJ), Antonio A. F. Oliveira (COPPE/UFRJ), Gilson A. Giraldi (LNCC), Yalmar P. Atencio (COPPE/UFRJ).

Abstract: This video shows the results obtained with our computational framework to incorporate rain in real videos. The rain simulation method takes alpha mattes from a database which is generated from rain videos. Then, the raindrops are modeled by a particle system implemented in GPU. Each particle represents a drop and it is rendered using the alpha matte and the Precomputed Radiance Transfer (PRT), expressed in spherical harmonics, which is used to incorporate environment lightning to the rendering engine. Thus, the appearance of rain change with the environment map (video-frame) in real-time. The spherical form of the drop model allows that the radiance transfer function (RTF) for any outgoing direction has a closed form expression. We remark that this makes its evaluation much faster since there is no need of tracing the light inside the drop.

Length: 2 min 6 sec

Geotextures: A Multi-Source Geodesic Distance Field Approach for Procedural Texturing of Complex Meshes

Authors: Guilherme N. Oliveira (UFRGS), Rafael P. Torchelsen (UFRGS), João L. D. Comba (UFRGS), Marcelo Walter (UFRGS), Rui Bastos (NVIDIA).

Abstract: Texture mapping is an important technique to add visual detail to geometric models. As an alternative to traditional image-based texture mapping, procedural textures are described by a function, with interesting properties such as compact representation, resolution independency and parametric adjustment of the visual appearance. Procedural textures are usually defined in the 2D texture space, making the result dependent on texture mapping coordinates assigned to the model, or in the 3D object space, implying in no correlation with the surface model. In this work we introduce GeoTextures, an approach that uses the geodesic distance, defined from multiple sources over the model, as a parameter that is taken into account by time-varying procedural textures. The use of geodesic distances allows the process to be both independent from the mapping of texturing coordinates and also conforming with the model surface. We validate the proposal by applying real-time procedural textures in complex surfaces.

Length: 2 min 55 sec

Blood Vessel Tracking in MRA images

Authors: Maysa Malfisa Garcia de Macedo (IME/USP), Jesús Pascual Mena-Chalco (IME/USP), Choukri Mekkaoui (Harvard Medical School), Marcel Parolim Jackowski (IME/USP).

Abstract: Vascular disease is characterized by any condition that affects the circulatory system. Recently, a demand for sophisticated software tools that can characterize the integrity and functional state of vascular networks from different vascular imaging modalities has appeared. Such tools face significant challenges such as: large datasets, similarity in intensity distributions of other organs and structures, and the presence of complex vessel geometry and branching patterns. Towards that goal, this video presents a new approach to automatically track vascular networks from MRA images. Our methodology is based on the Hough transform to dynamically estimate the centerline and vessel diameter along the vessel trajectory. Furthermore, the vessel architecture and orientation is determined by the analysis of the Hessian matrix of the MRA intensity distribution. Results are shown using real human MRA images. The tracking algorithm yielded high reproducibility rates, robustness to different noise levels, associated with simplicity of execution, which demonstrates the feasibility of our approach.

Length: 2 min 59 sec

Computer Animation Shorts

The Adventures of the Klein Bottle

Authors: Konstantin Weixelbaum (FU Berlin), Ilkay Sakalli (FU Berlin), Konrad Polthier (FU Berlin).
Abstract: This animated short film gives never seen before views into the Klein Bottle, which was a breakthrough in surface topology. The Klein Bottle is a classic surface that fascinates mathematicians since it was first described as a “double surface” by the German geometer Felix Klein in 1882. Nowadays it is described as being non-orientable, that means it is onesided, there is no inside or outside – this property links it closely to the Moebius strip. The film shows the original notes of Klein and a wild ride over the surface of the Klein Bottle. The film was produced using Autodesk Maya: animations show how a flat paper can be transformed into the Klein Bottle, how two Moebius strips form a Klein Bottle and how a Figure 8 curve rotating with a half twist forms the Figure 8 Klein Bottle. Deformations were performed using a custom made MEL script, converting models from Javaview animations into Maya keyframe animations. The short film has an educational purpose: It teaches complex topics from differential geometry and topology in a very visual way and therefore make it also accessible and interesting to a general public that is drawn by the beauty of the Klein Bottle.
Length: 3 min 56 sec

Dance to the Music / Play to the Motion

Authors: Luiz Velho (Visgraf/IMPA), Marcelo Cicconet (Visgraf/IMPA), Adriana Schulz (Visgraf/IMPA), Bruno Madeira (Visgraf/IMPA).
Abstract: In this video we illustrate how the analysis of a samba dancer’s movement can be used to synthesize an original samba-style music piece. First, the dance is captured using motion capture technology. Then, the performance is segmented according to the boundaries of the musical phrases, and the similarities between movements are analyzed in order to build a measuresynchronous motion graph. Finally, a constrained random walk in such a graph guides the composition of a new song. The automatic composition algorithm makes use of high level parameters, such as the melody instrument and the number of notes per beat, which are provided by the random walk in the motion graph.
Length: 2 min 29 sec

CG Chorus Line

Authors: Luiz Velho (Visgraf/IMPA), Marcelo Cicconet (Visgraf/IMPA), Adriana Schulz (Visgraf/IMPA), Bruno Madeira (Visgraf/IMPA), Aldo René Zang (Visgraf/IMPA), Carlos Eduardo da Cruz (Visgraf/IMPA).
Abstract: This video is an extension of our previous work for dance-guided music composition: Dance to the Music / Play to the Motion. Following the ideas of this work, a measure-synchronous motion graph, built from motion captured data, is used as a tool to guide the concatenation of musical phrases for the composition of a new dance and corresponding song. In addition, we have built a chorus line from a single dance movement, by implementing variations on time and scale, in order to guarantee natural and realistic motions. The music composition algorithm was also modified to include additional instruments, generating a more vibrant music piece, consistent with the context of multiple dancers.
Length: 1 min 23 sec

Ele Ela

Authors: Leo Issey Okumura (UNICAMP – FT), Rafael de Moraes Meneghel (UNICAMP – FT), Marco Antonio Garcia de Carvalho (UNICAMP – FT).
Abstract: A animação apresenta de maneira musical e alegre o início do namoro entre os dois personagens principais: Ele e Ela. A animação foi construída em 3D e totalmente desenvolvida no software Blender.
Length: 1 min 58 sec

As Aventuras de Bruford e Calahan

Authors: Ricardo Pinto Paiva (UFRN), Adriano Sabino (UFRN), Emanuel Diniz (UFRN).
Abstract: Apresentado como curta metragem para a disciplina de Direção em TV, do curso de Comunicação Social com habilitação em Radialismo, da Universidade Federal do Rio Grande do Norte, sob orientação do professor Ms. Ruy Alkmin Rocha Filho, “As aventuras de Bruford e Calahan” é um curta de animação no estilo stop-motion com algumas cenas em vídeo, onde narra, de forma divertida, os duelo entre dois pistoleiros.
Length: 5 min 54 sec

Levels of Abstraction

Authors: Mára Regina Labuto Fragoso da Silva (UFES), Caio Philipe Vargas de Souza (UFES), Izon Thomaz Mielke (UFES), Marcelo Valentim de Oliveira (UFES), Roberto Carraretto (UFES).
Abstract: This video results from part of the Computer Graphics (emphasis on Image Processing) discipline evaluation at Espirito Santo Federal University for Computer Engineering and Computer Science courses. This evaluation was concerned on, keeping in mind the discipline programmatic content, make use of a practical and playful approach. The students had to make a short film composed by processed images (frames), applying studied techniques, and implementing them in MATLAB software. Besides this, they had to employ creativity, since the theme was free. The theme of the film is From Micro to Macro: superstrings, athom, molecule, DNA, blood cells, heart, fertilization, baby, people, city, Mars/Earth, explosion, stars, galaxies, universe, Milky Way, multiverses. Among the techniques used by this work, we can notice: color transforms; rotation; cropping; histogram adjusting; geometrical transforms; special filters (Wiener, median, motion); arithmetic operations; binarization; morphological operations; morphing; image adjusting (gamma); salt and pepper noise insert and removal; zooming; sin functions.
Length: 2 min 45 sec

O Trabalho de Programação

Authors: Mára Regina Labuto Fragoso da Silva (UFES), Caroline Rizzi Raymundo (UFES), Jessiele Paulo Rodrigues (UFES), Letícia Camara Martins (UFES), Rodolfo Gusson (UFES), Wagner Soares de Oliveira (UFES).
Abstract: This video results from part of the Computer Graphics (emphasis on Image Processing) discipline evaluation at Espirito Santo Federal University for Computer Engineering and Computer Science courses. This evaluation was concerned on, keeping in mind the discipline programmatic content, make use of a practical and playful approach. The students had to make a short film composed by processed images (frames), applying studied techniques, and implementing them in MATLAB software. Besides this, they had to employ creativity, since the theme was free. The theme of the film is the journey of a Computer Science student from the moment of the professor’s solicitation of a job until the moment of the delivery of it. Among the techniques used by this work, we can notice: morphing; rotation; dithering; Gaussian, Poisson, speckle and salt and pepper noise insert and removal; color transforms.
Length: 2 min 56 sec

Buba e o Aquecimento Global/ Buba and the Global Warming

Authors: Rodrigo Olaio Pereira (Mono 3D), Eduardo Nakamura (Mono 3D).
Abstract: Buba é um projeto de animação 3D que retrata a relação bem humorada entre um homem das cavernas e seu dinossauro de estimação. Através de paralelos inteligentes para representar os recursos naturais que utilizamos atualmente, “Buba” mostra, de maneira divertida e educativa, os impactos causados no meio ambiente pelos maus hábitos do homem moderno. Em “Buba e O Aquecimento Global”, Buba e seu companheiro Dino, aprenderão sobre os fatores causadores do aquecimento global e seus efeitos.
Length: 1 min

A Perna Cabeluda

Authors: Victor Almeida (SAGA), Bruno Felix (SAGA), Rodolfo Borges (SAGA), Marilia Feldhues (SAGA), Emanuel Nascimento (SAGA), Harrison Costa (SAGA), Ridson Elias (SAGA), Yuri Zaidan (SAGA), Marcio Rocha (SAGA), Klebson dos Santos (SAGA), Magnum Gerson (SAGA), Cesar Araujo (SAGA), Alisson Henrique (SAGA), Dhavy Henrique (SAGA), Jesuíne Nóbrega (SAGA), Leonardo Lobo (SAGA), Eduarda Lobo (SAGA), Rodrigo Rodrigues (SAGA), Nicolas Haver (SAGA), Andyson Rafael da Silva (SAGA), Ana Claudia Ramos (SAGA), Cleison Amorin (SAGA), Maria Eduarda Mendes (SAGA), Felipe Jorge Pereira (SAGA), Stephano Breitt (SAGA), Jefferson de Araújo (SAGA), Joáo Victor Leite (SAGA), Ricardo Souza (SAGA), Thiago Oliveira (SAGA), Rafael Batista (SAGA), Luciano Neto (SAGA), Tiago Lemos de Araujo Machado (CESAR/SAGA), Marlio Silva (SAGA), Hermes Leonardo Ferreira (SAGA), Rafael Suarez (SAGA).
Abstract: A Perna Cabeluda (The Hairy Leg) is a short movie about one of the most popular urban legends in Recife. The number of people who attributed mysterious attacks to the single leg (without a body) in the Recife Antigo region had increased by years and brought fame to this kind of monster. The movie utilize of humor and thrilling scenes to tell the story of a man who ignores this myth, but was chased by it! The film technical sequences were entirely based in the tools provided by the Adobe Creative Suite 4. Adobe Premiere allowed the audio/video edition process, Adobe After Effects was utilized to create the overture and credits scenes, Adobe Ilustrator, Flash and Photoshop were utilized to develop the characters, scenarios and all the animation sequences.
Length: 3 min 56 sec


Authors: Soraia Raupp Musse (PUCRS), Henry Braun (PUCRS), Mauricio Gehling (PUCRS).
Abstract: This video shows a story about a call for proposals edited in 2014, which the goal is to re-create the world, ended in 2012. For this video, we included various shots of technical and modeling algorithms, developed and used in VHLab – Virtual Human Laboratory at PUCRS.
Length: 4 min 24 sec