-
1
-
2
Interactivity and authenticity in AI-augmented videos
Published 2022“…How would such alterations colour the underlying information in the videos? In such a world, would the viewer be able to tell apart the synthesized from the real? …”
Get full text
Thesis -
3
Restoring Eye Contact in Video Conferencing
Published 2023“…This work proposes the application of a Convolutional Neural Network (CNN) based 3D face reconstruction technique, Position Map Regression Network (PRNet), on 2D images from a single RGB webcam found in consumer-grade computers to create a newly synthesized video stream where the video conferencing user’s face becomes oriented towards the webcam, resolving the physical deviation between the webcam location and the location of the other participant shown on the screen. …”
Get full text
Thesis -
4
-
5
Novel View Synthesis from Casually Recorded Videos
Published 2022“…Generating new, photorealistic views of a scene given only a single video is a difficult task that computer vision researchers have worked on for decades. …”
Get full text
Thesis -
6
-
7
A Pipeline for Synthesizing Action-conditioned Human Motion from Raw Motion Capture Data
Published 2023“…In many sports, less-experienced trainees will often draw inspiration from videos of experts. While this can be an effective tool for improvement, this process lacks the ability for the trainee to specifically focus on improving their skills based on the limitations of their current abilities, body type, and weaknesses. …”
Get full text
Thesis -
8
Text-Free Audio Captions of Short Videos from Latent Space Representation
Published 2022“…We alter the models to process video data rather than image data and analyze the resulting speech captions. …”
Get full text
Thesis -
9
-
10
-
11
-
12
Depth frame loss concealment for wireless transmission utilising motion detection information
Published 2014“…On top of that, existing error concealment algorithms for the 2D videos are not suitable to apply to the 3D video and they may even degrade the quality of the synthesized view in the 3D video. …”
Get full text
Thesis -
13
-
14
-
15
Self-Supervised Audio-Visual Speech Diarization and Recognition
Published 2024“…A complementary synthesized dataset is constructed by mixing audio and video samples from LRS3 at varying overlap thresholds, resulting in the LRS3Mix dataset. …”
Get full text
Thesis -
16
Motion-Compensated Viewpoint Shift
Published 2024“…Eye contact is an essential social cue that conveys our attention to others but is difficult to maintain during video calls. Many existing methods to synthesize a gaze-corrected view involve estimating a 3D face model and projecting it into the desired camera view, which is too computationally expensive for most personal computers. …”
Get full text
Thesis -
17
-
18
-
19
-
20