In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA.
We reformulate the NeRF to also directly output the visibility of a 3D point from a given viewpoint to reduce the training time with the visibility constraint.
Designing learning-based no-reference (NR) video quality assessment (VQA) algorithms for camera-captured videos is cumbersome due to the requirement of a large number of human annotations of quality.
The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs.
The predicted object motion is then integrated with the given user or camera motion to generate the next frame.
Ranked #1 on Video Prediction on MPI Sintel
Completely blind video quality assessment (VQA) refers to a class of quality assessment methods that do not use any reference videos, human opinion scores or training videos from the target database to learn a quality model.
Challenges in capturing aligned low light and well-lit image pairs and collecting a large number of human opinion scores of quality for training, warrant the design of unsupervised (or opinion unaware) no-reference (NR) QA methods.
We consider the problem of temporal view synthesis, where the goal is to predict a future video frame from the past frames using knowledge of the depth and relative camera motion.
Ranked #1 on Temporal View Synthesis on SceneNet RGB-D
We show that our feature design leads to state of the art quality prediction in accordance with human judgments on our IISc PVQA Database.