1 code implementation • 27 Dec 2022 • Kihong Kim, Yunho Kim, Seokju Cho, Junyoung Seo, Jisu Nam, Kychul Lee, Seungryong Kim, Kwanghee Lee
In this paper, we propose a diffusion-based face swapping framework for the first time, called DiffFace, composed of training ID conditional DDPM, sampling with facial guidance, and a target-preserving blending.
3 code implementations • 21 Mar 2023 • Seokju Cho, Heeseong Shin, Sunghwan Hong, Anurag Arnab, Paul Hongsuck Seo, Seungryong Kim
Open-vocabulary semantic segmentation presents the challenge of labeling each pixel within an image based on a wide range of text descriptions.
Ranked #1 on Open Vocabulary Semantic Segmentation on ADE20K-150
2 code implementations • 22 Dec 2021 • Sunghwan Hong, Seokju Cho, Jisu Nam, Seungryong Kim
We introduce a novel cost aggregation network, dubbed Volumetric Aggregation with Transformers (VAT), to tackle the few-shot segmentation task by using both convolutions and transformers to efficiently handle high dimensional correlation maps between query and support.
Ranked #3 on Semantic correspondence on PF-WILLOW
1 code implementation • 22 Jul 2022 • Sunghwan Hong, Seokju Cho, Jisu Nam, Stephen Lin, Seungryong Kim
However, the tokenization of a correlation map for transformer processing can be detrimental, because the discontinuity at token boundaries reduces the local context available near the token edges and decreases inductive bias.
Ranked #2 on Semantic correspondence on PF-WILLOW
1 code implementation • CVPR 2023 • JiHye Park, Sunwoo Kim, Soohyun Kim, Seokju Cho, Jaejun Yoo, Youngjung Uh, Seungryong Kim
Existing techniques for image-to-image translation commonly have suffered from two critical problems: heavy reliance on per-sample domain annotation and/or inability of handling multiple attributes per image.
1 code implementation • NeurIPS 2021 • Seokju Cho, Sunghwan Hong, Sangryul Jeon, Yunsung Lee, Kwanghoon Sohn, Seungryong Kim
We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images with additional challenges posed by large intra-class appearance and geometric variations.
Ranked #5 on Semantic correspondence on PF-WILLOW
1 code implementation • 6 Oct 2022 • Sunghwan Hong, Jisu Nam, Seokju Cho, Susung Hong, Sangryul Jeon, Dongbo Min, Seungryong Kim
Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters.
1 code implementation • 22 Sep 2022 • Junyoung Seo, Gyuseong Lee, Seokju Cho, Jiyoung Lee, Seungryong Kim
Specifically, we formulate a diffusion-based matching-and-generation framework that interleaves cross-domain matching and diffusion steps in the latent space by iteratively feeding the intermediate warp into the noising process and denoising it to generate a translated image.
1 code implementation • 30 May 2023 • Jiuhn Song, Seonghoon Park, Honggyu An, Seokju Cho, Min-Seop Kwak, SungJin Cho, Seungryong Kim
Employing monocular depth estimation (MDE) networks, pretrained on large-scale RGB-D datasets, with powerful generalization capability would be a key to solving this problem: however, using MDE in conjunction with NeRF comes with a new set of challenges due to various ambiguity problems exhibited by monocular depths.
1 code implementation • 14 Feb 2022 • Seokju Cho, Sunghwan Hong, Seungryong Kim
Cost aggregation is a highly important process in image matching tasks, which aims to disambiguate the noisy matching scores.
Ranked #3 on Semantic correspondence on PF-PASCAL
no code implementations • 25 Jan 2022 • Jiwon Kim, Kwangrok Ryoo, Gyuseong Lee, Seokju Cho, Junyoung Seo, Daehwan Kim, Hansang Cho, Seungryong Kim
In this paper, we address this limitation with a novel SSL framework for aggregating pseudo labels, called AggMatch, which refines initial pseudo labels by using different confident instances.
no code implementations • 19 Sep 2022 • Sunghwan Hong, Seokju Cho, Seungryong Kim, Stephen Lin
The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggregation.
Ranked #1 on Geometric Matching on HPatches
no code implementations • 17 Mar 2024 • Sunghwan Hong, Seokju Cho, Seungryong Kim, Stephen Lin
In this work, we first show that feature aggregation and cost aggregation exhibit distinct characteristics and reveal the potential for substantial benefits stemming from the judicious use of both aggregation processes.