Range-Nullspace Video Frame Interpolation With Focalized Motion Estimation
Continuous-time video frame interpolation is a fundamental technique in computer vision for its flexibility in synthesizing motion trajectories and novel video frames at arbitrary intermediate time steps. Yet, how to infer accurate intermediate motion and synthesize high-quality video frames are two critical challenges. In this paper, we present a novel VFI framework with improved treatment for these challenges. To address the former, we propose focalized trajectory fitting, which performs confidence-aware motion trajectory estimation by learning to pay focus to reliable optical flow candidates while suppressing the outliers. The second is range-nullspace synthesis, a novel frame renderer cast as solving an ill-posed problem addressed by learning decoupled components in orthogonal subspaces. The proposed framework sets new records on 7 of 10 public VFI benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
Video Frame InterpolationSimilar Papers 제목 키워드 기반
Video Interpolation and Prediction with Unsupervised Landmarks
Prediction and interpolation for long-range video data involves the complex task of modeling motion trajectories for each visible object, occlusions and dis-occlusions, as well as appearance changes due to viewpoint and …
DecoderMotion InterpolationOptical Flow EstimationPrediction+1Texture-aware Video Frame Interpolation
Temporal interpolation has the potential to be a powerful tool for video compression. Existing methods for frame interpolation do not discriminate between video textures and generally invoke a single general model capabl…
Texture ClassificationVideo CompressionVideo Frame InterpolationDevelopment of aging changes: self-accelerating and inhomogeneous
Aging changes including age spots and atherosclerotic plaques develop in an inhomogeneous and accelerated manner. For understanding this phenomenon, some aging changes are analyzed by Misrepair mechanism, a mechanism pro…
SensitivityRAI-Net: Range-Adaptive LiDAR Point Cloud Frame Interpolation Network
LiDAR point cloud frame interpolation, which synthesizes the intermediate frame between the captured frames, has emerged as an important issue for many applications. Especially for reducing the amounts of point cloud tra…
Video Frame InterpolationNullSpaceNet: Nullspace Convoluional Neural Network with Differentiable Loss Function
We propose NullSpaceNet, a novel network that maps from the pixel level input to a joint-nullspace (as opposed to the traditional feature space), where the newly learned joint-nullspace features have clearer interpretati…