21 citations · 64 across the 23 of their papers we have counts for
23 papers
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
Seokju Cho, Ryo Hachiuma, Abhishek Badki +8
Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-aug…
4DP-QA: Scalable QA for 4D Perception in Vision Language Models
Seokju Cho, Abhishek Badki, Hang Su +5
Despite recent advances, Vision Language Models (VLMs) still struggle to grasp the dynamics of the world. We note that the ability to reason about a 4D scene, challenging in itself…
MV-TAP: Tracking Any Point in Multi-View Videos
Jahyeok Koo, Inès Hyeonsu Kim, Mungyeom Kim +6
Multi-view camera systems enable rich observations of complex real-world scenes, and understanding dynamic objects in multi-view settings has become central to various applications…
AnthroTAP: Learning Point Tracking with Real-World Motion
Inès Hyeonsu Kim, Seokju Cho, Jahyeok Koo +5
Point tracking models often struggle to generalize to real-world videos because large-scale training data is predominantly synthetic$\unicode{x2014}$the only source currently feasi…
Seurat: From Moving Points to Depth
Seokju Cho, Jiahui Huang, Seungryong Kim +1
Accurate depth estimation from monocular videos remains challenging due to ambiguities inherent in single-view geometry, as crucial depth cues like stereopsis are absent. However,…
Exploring Temporally-Aware Features for Point Tracking
Inès Hyeonsu Kim, Seokju Cho, Jiahui Huang +3
Point tracking in videos is a fundamental task with applications in robotics, video editing, and more. While many vision tasks benefit from pre-trained feature backbones to improve…
Multi-Granularity Video Object Segmentation
Sangbeom Lim, Seongchan Kim, Seungjun An +3
Current benchmarks for video segmentation are limited to annotating only salient objects (i.e., foreground instances). Despite their impressive architectural designs, previous work…
Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
Heeseong Shin, Chaehyun Kim, Sunghwan Hong +4
Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present. How…
Local All-Pair Correspondence for Point Tracking
Seokju Cho, Jiahui Huang, Jisu Nam +3
We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely…
Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification
Inès Hyeonsu Kim, Woojeong Jin, Soowon Son +6
Person re-identification (Re-ID) often faces challenges due to variations in human poses and camera viewpoints, which significantly affect the appearance of individuals across imag…
Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
Sunghwan Hong, Seokju Cho, Seungryong Kim +1
This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit f…
DaRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation
Jiuhn Song, Seonghoon Park, Honggyu An +4
Neural radiance fields (NeRF) shows powerful performance in novel view synthesis and 3D geometry reconstruction, but it suffers from critical performance degradation when the numbe…
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
Seokju Cho, Heeseong Shin, Sunghwan Hong +3
Open-vocabulary semantic segmentation presents the challenge of labeling each pixel within an image based on a wide range of text descriptions. In this work, we introduce a novel c…
DiffFace: Diffusion-based Face Swapping with Facial Guidance
Kihong Kim, Yunho Kim, Seokju Cho +5
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, an…
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Sunghwan Hong, Jisu Nam, Seokju Cho +4
Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters. Th…
Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence
Sunghwan Hong, Seokju Cho, Seungryong Kim +1
We present a novel architecture for dense correspondence. The current state-of-the-art are Transformer-based approaches that focus on either feature descriptors or cost volume aggr…
MIDMs: Matching Interleaved Diffusion Models for Exemplar-based Image Translation
Junyoung Seo, Gyuseong Lee, Seokju Cho +2
We present a novel method for exemplar-based image translation, called matching interleaved diffusion models (MIDMs). Most existing methods for this task were formulated as GAN-bas…
LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data
Jihye Park, Sunwoo Kim, Soohyun Kim +4
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 mu…
Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
Sunghwan Hong, Seokju Cho, Jisu Nam +2
This paper presents a novel cost aggregation network, called Volumetric Aggregation with Transformers (VAT), for few-shot segmentation. The use of transformers can benefit correlat…
CATs++: Boosting Cost Aggregation with Convolutions and Transformers
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. Existing methods generally tackle this by hand-crafted…
AggMatch: Aggregating Pseudo Labels for Semi-Supervised Learning
Jiwon Kim, Kwangrok Ryoo, Gyuseong Lee +5
Semi-supervised learning (SSL) has recently proven to be an effective paradigm for leveraging a huge amount of unlabeled data while mitigating the reliance on large labeled data. C…
Cost Aggregation Is All You Need for Few-Shot Segmentation
Sunghwan Hong, Seokju Cho, Jisu Nam +1
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 transf…
CATs: Cost Aggregation Transformers for Visual Correspondence
Seokju Cho, Sunghwan Hong, Sangryul Jeon +3
We propose a novel cost aggregation network, called Cost Aggregation Transformers (CATs), to find dense correspondences between semantically similar images with additional challeng…