Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟮𝟭𝟰 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗟𝗶𝘁𝗲𝗙𝗹𝗼𝘄𝗡𝗲𝘁𝟯: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation by Nanyang Technological University Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in ECCV2020 with over 9 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/dNrgDz2 code : https://lnkd.in/dWbUyW4 ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸Deep learning approaches have achieved great success in addressing the problem of optical flow estimation. The keys to success lie in the use of cost volume and coarse-to-fine flow inference. 🔸However, the matching problem becomes ill-posed when partially occluded or homogeneous regions exist in images. This causes a cost volume to contain outliers and affects the flow decoding from it. 🔸Besides, the coarse-to-fine flow inference demands an accurate flow initialization. Ambiguous correspondence yields erroneous flow fields and affects the flow inferences in subsequent levels. 🔸In this paper, we introduce LiteFlowNet3, a deep network consisting of two specialized modules, to address the above challenges. (1) We ameliorate the issue of outliers in the cost volume by amending each cost vector through an adaptive modulation prior to the flow decoding. (2) We further improve the flow accuracy by exploring local flow consistency. 🔸To this end, each inaccurate optical flow is replaced with an accurate one from a nearby position through a novel warping of the flow field. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime. #computervision #artificialintelligence #deeplearning