Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleDecember 2018
On the convergence and mode collapse of GAN
SA '18: SIGGRAPH Asia 2018 Technical BriefsDecember 2018, Article No.: 21, Pages 1–4https://doi.org/10.1145/3283254.3283282Generative adversarial network (GAN) is a powerful generative model. However, it suffers from several problems, such as convergence instability and mode collapse. To overcome these drawbacks, this paper presents a novel architecture of GAN, which ...
- research-articleDecember 2018
Reconstruction of volumetric reflectance using spatio-sequential frequency correlation imaging
SA '18: SIGGRAPH Asia 2018 Technical BriefsDecember 2018, Article No.: 19, Pages 1–4https://doi.org/10.1145/3283254.3283278In this paper, we propose a novel pro-cam technique for reconstruction of the volumetric reflectance inside an object. The key concept is use of spatio-sequentially modulated illumination to extract only the required signal at a 3D point. We discovered ...
- research-articleDecember 2018
Recurrent transition networks for character locomotion
SA '18: SIGGRAPH Asia 2018 Technical BriefsDecember 2018, Article No.: 4, Pages 1–4https://doi.org/10.1145/3283254.3283277We present a novel approach, based on deep recurrent neural networks, to automatically generate transition animations given a past context of a few frames, a target character state and optionally local terrain information. The proposed Recurrent ...
- research-articleDecember 2018
Removing objects from videos with a few strokes
SA '18: SIGGRAPH Asia 2018 Technical BriefsDecember 2018, Article No.: 22, Pages 1–4https://doi.org/10.1145/3283254.3283276We present a system for the removal of objects from videos. As an input, the system only needs a user to draw a few strokes in at least one frame, roughly delimiting the objects to be removed. These rough masks are then automatically refined and ...
- research-articleDecember 2018
Accurate 3D locating and tracking of basketball players from multiple videos
SA '18: SIGGRAPH Asia 2018 Technical BriefsDecember 2018, Article No.: 27, Pages 1–4https://doi.org/10.1145/3283254.3283265With the development of pedestrian detection technologies, existing methods cannot simultaneously satisfy high-quality detection and fast calculation for practical applications, especially for accurate 3D locating and tracking of basketball players. We ...
- research-articleDecember 2018
Dunhuang mural restoration using deep learning
SA '18: SIGGRAPH Asia 2018 Technical BriefsDecember 2018, Article No.: 23, Pages 1–4https://doi.org/10.1145/3283254.3283263As time goes by, the art pieces inside Dunhuang Grottoes have suffered from tremendous damage such as mural deterioration, and they are usually difficult to be repaired. Although we can achieve digital preservation by modeling the caves and preserving ...
- research-articleDecember 2018
Gourmet photography dataset for aesthetic assessment of food images
SA '18: SIGGRAPH Asia 2018 Technical BriefsDecember 2018, Article No.: 20, Pages 1–4https://doi.org/10.1145/3283254.3283260In this study, we present the Gourmet Photography Dataset (GPD), which is the first large-scale dataset for aesthetic assessment of food photographs. We collect 12,000 food images together with human-annotated labels (i.e., aesthetically positive or ...
- research-articleDecember 2018
Optimal and interactive keyframe selection for motion capture
SA '18: SIGGRAPH Asia 2018 Technical BriefsDecember 2018, Article No.: 26, Pages 1–4https://doi.org/10.1145/3283254.3283256Motion capture is increasingly used in games and movies. However, it often requires editing before it can be used. Unfortunately, editing is laborious because of the low-level representation of the data. Existing motion editing methods accomplish modest ...