We present a new approach to the video matting problem which improves the temporal coherency. In existing video matting approaches the alpha matte sequence is determined frame by frame, which leads to flickering near the boundary of the extracted foreground region. Especially the temporal artifacts

temporal coherence. A method for caching contact forces is presented that allows con-tact points to move from step to step and to appear and disappear. Examples are provided to illustrate the effectiveness of the algorithm. 1

We discuss data involving the temporal structure of connected discourse. Questions are raised about the relation between clause order in discourse and causal order in the world, and about the coherence of certain discourses. We maintain that interpretation is contextually influenced by knowledge

Precomputed radiance transfer (PRT) enables all-frequency relighting with complex illumination, materials and shadows. To achieve real-time performance, PRT exploits angular coherence in the illumination, and spatial coherence in the light transport. Temporal coherence of the lighting from frame

Temporal coherence is crucial in content-aware video retargeting. To date, this problem has been addressed by constraining temporally adjacent pixels to be transformed coherently. However, due to the motion-oblivious nature of this simple constraint, the retargeted videos often exhibit flickering

Abstract. Extracting temporally-coherent alpha mattes in video is an important but challenging problem in post-production. Previous video matting systems are highly sensitive to initial conditions and image noise, thus cannot reliably produce stable alpha mattes without tem-poral jitter

In this paper we address the problem of learning Gaussian Mixture Models (GMMs) incrementally. Unlike previous approaches which universally assume that new data comes in blocks representable by GMMs which are then merged with the current model estimate, our method works for the case when novel data points arrive oneby -one, while requiring little additional memory. We keep only two GMMs in the memory and no historical data. The current fit is updated with the assumption that the number of components is fixed, which is increased (or reduced) when enough evidence for a new component is seen. This is deduced from the change from the oldest fit of the same complexity, termed the Historical GMM, the concept of which is central to our method. The performance of the proposed method is demonstrated qualitatively and quantitatively on several synthetic data sets and video sequences of faces acquired in realistic imaging conditions.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci-entific research documents, whether they are pub-lished or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et a ̀ la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

We present a novel shape completion technique for creating temporally coherent watertight surfaces from real-time captured dynamic performances. Because of occlusions and low surface albedo, scanned mesh sequences typically exhibit large holes that persist over extended periods of time. Most

Producing high quality animations featuring rich object appearance and compelling lighting effects is very time consuming using traditional frame-by-frame rendering systems. In this paper we present a number of global illumination and rendering solutions that exploit temporal coherence in lighting