Timezone: »

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Sunghwan Hong · Jisu Nam · Seokju Cho · Susung Hong · Sangryul Jeon · Dongbo Min · Seungryong Kim

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #218

Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters. This architecture, however, inevitably results in a low-resolution matching field that additionally requires an ad-hoc interpolation process as a post-processing for converting it into a high-resolution one, certainly limiting the overall performance of matching results. To overcome this, inspired by recent success of implicit neural representation, we present a novel method for semantic correspondence, called Neural Matching Field (NeMF). However, complicacy and high-dimensionality of a 4D matching field are the major hindrances, which we propose a cost embedding network to process a coarse cost volume to use as a guidance for establishing high-precision matching field through the following fully-connected network. Nevertheless, learning a high-dimensional matching field remains challenging mainly due to computational complexity, since a na\"ive exhaustive inference would require querying from all pixels in the 4D space to infer pixel-wise correspondences. To overcome this, we propose adequate training and inference procedures, which in the training phase, we randomly sample matching candidates and in the inference phase, we iteratively performs PatchMatch-based inference and coordinate optimization at test time. With these combined, competitive results are attained on several standard benchmarks for semantic correspondence. Code and pre-trained weights are available at~\url{https://ku-cvlab.github.io/NeMF/}.

Author Information

Sunghwan Hong (Korea University)
Jisu Nam (Korea University)
Seokju Cho (Korea University)
Susung Hong (Korea University)
Sangryul Jeon (Electrical Engineering & Computer Science Department, University of California, Berkeley)
Dongbo Min (Ewha Womans University)
Seungryong Kim (Korea University)

More from the Same Authors