This is the 15th edition of the European Conference on Visual Media Production (CVMP) and the first time that the conference has had full ACM SIGGRAPH sponsored status. CVMP has built a reputation as the prime venue for researchers to meet with practitioners in the Creative Industries and brings together production and post-production specialists from the worlds of film, broadcast and games with imaging and graphics researchers. It brings together expertise in video processing, computer vision, computer graphics, animation and physical simulation. Once again, we are delighted that CVMP this year will be hosted by the British Film Institute in London, UK.
Proceeding Downloads
Feature-preserving detailed 3D face reconstruction from a single image
Dense 3D face reconstruction plays a fundamental role in visual media production involving digital actors. We improve upon high fidelity reconstruction from a single 2D photo with a reconstruction framework that is robust to large variations in ...
Combining dense nonrigid structure from motion and 3D morphable models for monocular 4D face reconstruction
Monocular 4D face reconstruction is a challenging problem, especially in the case that the input video is captured under unconstrained conditions, i.e. "in the wild". The majority of the state-of-the-art approaches build upon 3D Morphable Modelling (...
Director's cut: a combined dataset for visual attention analysis in cinematic VR content
Methods of storytelling in cinema have well established conventions that have been built over the course of its history and the development of the format. In 360° film many of the techniques that have formed part of this cinematic language or visual ...
Development of laparoscopic cholecystectomy simulator based on unity game engine
Fast development of the minimally invasive surgery (MIS) technology demands extra surgical skills training to meet advanced technological challenges. However, massive capital expenditures and ethical issues with safety considerations exist in ...
Lie bodies based 3D shape morphing and interpolation
Morphing and Interpolation algorithms aim to support the animator by automating animation in two scenarios. While morphing algorithms generate intermediate objects given two (or more) objects belonging to different classes, interpolation generates ...
DeepCalib: a deep learning approach for automatic intrinsic calibration of wide field-of-view cameras
Calibration of wide field-of-view cameras is a fundamental step for numerous visual media production applications, such as 3D reconstruction, image undistortion, augmented reality and camera motion estimation. However, existing calibration methods ...
Sequence alignment with the hilbert-schmidt independence criterion
We present a technique for establishing the temporal alignment between two videos of a single scene, by measuring the statistical dependence between the videos using the Hilbert-Schmidt independence criterion. Unlike previous approaches our technique ...
Method of optimal directions for visual tracking
Sparse representation is widely used in visual tracking thanks to its efficiency and ability to handle appearance changes. In this paper, we propose to improve the original mean shift tracking algorithm, by defining its target model and candidates with ...
Cited By
-
Sun Y, Sun P, Dong M, Liu Q, Dai G, Yan B, Wang J, Ehret G, Chen B and Han S (2024). A precise and robust calibration method for fisheye cameras Optical Metrology and Inspection for Industrial Applications XI, 10.1117/12.3037102, 9781510682108, (71)
-
Miyazaki R, Hayashi Y, Oda M, Mori K, Išgum I and Colliot O (2023). Octree cube constraints in PBD method for high resolution surgical simulation Image Processing, 10.1117/12.2654092, 9781510660335, (104)
Index Terms
- Proceedings of the 15th ACM SIGGRAPH European Conference on Visual Media Production