Longliang Liu
YOU?
Author Swipe
View article: SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion
SVDC: Consistent Direct Time-of-Flight Video Depth Completion with Frequency Selective Fusion Open
Lightweight direct Time-of-Flight (dToF) sensors are ideal for 3D sensing on mobile devices. However, due to the manufacturing constraints of compact devices and the inherent physical principles of imaging, dToF depth maps are sparse and n…
View article: MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors
MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors Open
We introduce MonSter++, a geometric foundation model for multi-view depth estimation, unifying rectified stereo matching and unrectified multi-view stereo. Both tasks fundamentally recover metric depth from correspondence search and conseq…
View article: FlowDA: Unsupervised Domain Adaptive Framework for Optical Flow Estimation
FlowDA: Unsupervised Domain Adaptive Framework for Optical Flow Estimation Open
Collecting real-world optical flow datasets is a formidable challenge due to the high cost of labeling. A shortage of datasets significantly constrains the real-world performance of optical flow models. Building virtual datasets that resem…
View article: MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching
MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo Matching Open
Stereo matching is a fundamental task in scene comprehension. In recent years, the method based on iterative optimization has shown promise in stereo matching. However, the current iteration framework employs a single-peak lookup, which st…