Search Results for author:
Found 7 papers, 0 papers with code
SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations
Optical flow estimation is crucial to a variety of vision tasks.
OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolation
We propose OCAI, a method that supports robust frame interpolation by generating intermediate video frames alongside optical flows in between.
DIFT: Dynamic Iterative Field Transforms for Memory Efficient Optical Flow
Also, we present a novel dynamic coarse-to-fine cost volume processing during various stages of refinement to avoid multiple levels of cost volumes.
Guided Speech Enhancement Network
Multi-microphone speech enhancement problem is often decomposed into two decoupled steps: a beamformer that provides spatial filtering and a single-channel speech enhancement model that cleans up the beamformer output.
Efficient Heterogeneous Video Segmentation at the Edge
We introduce an efficient video segmentation system for resource-limited edge devices leveraging heterogeneous compute.
Imposing Consistency for Optical Flow Estimation
Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks.
Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices
To address this standing issue, we present a memory-aware compiler, dubbed SERENITY, that utilizes dynamic programming to find a sequence that finds a schedule with optimal memory footprint.
