Search Results for author:
Found 6 papers, 4 papers with code
Factorized Motion Fields for Fast Sparse Input Dynamic View Synthesis
However, the optimization with sparse input is under-constrained and necessitates the use of motion priors to constrain the learning.
SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions
The depth estimated by these simpler models is used to supervise the NeRF depth estimates.
ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields
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.
Temporal View Synthesis of Dynamic Scenes through 3D Object Motion Estimation with Multi-Plane Images
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
Revealing Disocclusions in Temporal View Synthesis through Infilling Vector Prediction
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
Understanding the Perceived Quality of Video Predictions
We show that our feature design leads to state of the art quality prediction in accordance with human judgments on our IISc PVQA Database.
