Author name cluster

DaeSik Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2024 Conference Paper

DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models

Namhyuk Ahn
Junsoo Lee
Chunggi Lee
Kunhee Kim
Daesik Kim
Seung-Hun Nam
Kibeom Hong

Recent progresses in large-scale text-to-image models have yielded remarkable accomplishments, finding various applications in art domain. However, expressing unique characteristics of an artwork (e.g. brushwork, colortone, or composition) with text prompts alone may encounter limitations due to the inherent constraints of verbal description. To this end, we introduce DreamStyle, a novel framework designed for artistic image synthesis, proficient in both text-to-image synthesis and style transfer. DreamStyle optimizes a multi-stage textual embedding with a context-aware text prompt, resulting in prominent image quality. In addition, with content and style guidance, DreamStyle exhibits flexibility to accommodate a range of style references. Experimental results demonstrate its superior performance across multiple scenarios, suggesting its promising potential in artistic product creation. Project page: https://nmhkahn.github.io/dreamstyler/

PDF Details DOI

AAAI Conference 2020 Conference Paper

Tell Me What They’re Holding: Weakly-Supervised Object Detection with Transferable Knowledge from Human-Object Interaction

Daesik Kim
Gyujeong Lee
Jisoo Jeong
Nojun Kwak

In this work, we introduce a novel weakly supervised object detection (WSOD) paradigm to detect objects belonging to rare classes that have not many examples using transferable knowledge from human-object interactions (HOI). While WSOD shows lower performance than full supervision, we mainly focus on HOI as the main context which can strongly supervise complex semantics in images. Therefore, we propose a novel module called RRPN (relational region proposal network) which outputs an object-localizing attention map only with human poses and action verbs. In the source domain, we fully train an object detector and the RRPN with full supervision of HOI. With transferred knowledge about localization map from the trained RRPN, a new object detector can learn unseen objects with weak verbal supervision of HOI without bounding box annotations in the target domain. Because the RRPN is designed as an add-on type, we can apply it not only to the object detection but also to other domains such as semantic segmentation. The experimental results on HICO-DET dataset show the possibility that the proposed method can be a cheap alternative for the current supervised object detection paradigm. Moreover, qualitative results demonstrate that our model can properly localize unseen objects on HICO-DET and V-COCO datasets.

PDF Details

ICRA Conference 2008 Conference Paper

Antipodal gray codes for structured light

DaeSik Kim
Moonwook Ryu
Sukhan Lee 0001

A Gray code and its variants are popular code-patterns for a structured light system. An n-bit Gray code is a kind of binary code whose adjacent code-strings differ only in one bit position. We introduce a specified Gray code, called an 'antipodal Gray code. ' Since the n-bit antipodal Gray code has the additional property that the complement of any code-string appears exactly n steps away in the list, the spatial frequency (the width between the white and black stripes) of the antipodal Gray code-pattern is similar along frames. In this paper, we describe the limitations of structured light and the criteria for robust codes. We evaluate the original and antipodal Gray codes, and the experimental results show that the antipodal Gray code provides more robust and accurate results than original Gray codes.

Details

ICRA Conference 2005 Conference Paper

A 3D IR Camera with Variable Structured Light for Home Service Robots

Sukhan Lee 0001
Jongmoo Choi
Seungmin Baek
Byungchan Jung
Changsik Choi
Hunmo Kim
Jeongtaek Oh
Seungsub Oh

There has shown a significant interest in a high performance of, at the same time, a compact size and low cost of, 3D sensor, in reflection of a growing need of 3D environmental sensing for service robotics. One of the important requirements associated with such a 3D sensor is that sensing does not irritate or disturb human in any way while working in close and continuous contact with human. Furthermore, such a 3D sensor should be reliable and robust to the change of environmental illumination as service robots are required to work day and night. This paper presents a 3D IR camera with variable structured light that is human friendly and robust enough for application to home service robots. Infrared is chosen as the sensing medium in order to meet the requirement of human friendliness and robustness to illumination change. A Digital Mirror Device (DMD) is employed to generate and project variable patterns at a high speed for real-time operation. In implementation, we emphasize the integration of modular components to support real-time sensing and compactness in size. A number of real-world experimentations are conducted, including a human face, a statue, and a plastic model. The experimental results have demonstrated that the implemented 3D IR Camera is robust to illumination change, in addition to its advantage of human friendliness.

Details

ICRA Conference 2005 Conference Paper

Signal Separation Coding for Robust Depth Imaging Based on Structured Light

Sukhan Lee 0001
Jongmoo Choi
DaeSik Kim
Jaekeun Na
Seungsub Oh

This paper presents an original approach to coding the light patterns for robust depth imaging based on structured light. We have discovered that the degradation of precision and robustness, seen in most conventional approaches to structured light, comes mainly from the overlapping of multiple codes in the signal received at a camera pixel, where the overlapped codes are from the neighbouring and/or, even, distant pixels of the projecting mirror array. Considering the criticality of separating the overlapped codes to precision and robustness, we propose a novel signal separation code, referred to here as “Hierarchical Orthogonal Code (HOC), ” for depth imaging. HOC provides not only the separation of overlapped codes, but also a robust decision on pixel correspondence with error correction based on a contextual likelihood among the sets of separated codes from neighbouring camera pixels. The experimental results have shown that the proposed HOC significantly enhances the robustness and precision in depth imaging, compared to the best known conventional approaches. The proposed approach opens a greater feasibility of applying structured light based depth imaging to a 3D modelling of cluttered workspace for home service robots.

Details