콜로퀴움
ENLARGING THE CAPABILITY OF DIFFUSION INVERSE SOLVERS BY GUIDANCE
등록일자 : 2024-02-13
예종철 교수(카이스트)
|
2024-02-22
|
판교 테크노밸리 산업수학혁신센터 세미나실
일시: 2024.2.22.(목), 14:00~16:00
장소: 판교 테크노밸리 산업수학혁신센터 세미나실
경기 성남시 수정구 대왕판교로 815, 기업지원허브 231호 국가수리과학연구소
무료주차는 2시간 지원됩니다.
발표자: 예종철 교수(카이스트)
주요내용: ENLARGING THE CAPABILITY OF DIFFUSION INVERSE SOLVERS BY GUIDANCE
The recent advent of diffusion models has led to significant progress in solving inverse problems, leveraging these models as effective generative priors. Nonetheless, challenges related to the ill-posed nature of such problems remain, such as 3D extension and overcoming inherent ambiguities in measurements. In this talk, we introduce strategies to address these issues. First, to enable 3D extension using only 2D diffusion models, we propose a novel approach using two perpendicular pre-trained 2D diffusion models which guides each solver to solve the 3D inverse problem. Specifically, by modeling the 3D data distribution as a product of 2D distributions sliced in different directions, our method effectively addresses the curse of dimensionality from the image guidance from the perpendicular direction. Second, drawing inspiration from the human ability to resolve visual ambiguities through perceptual biases, we introduce a novel latent diffusion inverse solver by incorporating guidance by text prompts. Specifically, our method applies the textual deion of the preconception of the solution during the reverse sampling phase, of which deion is dynamically reinforced through null-text optimization for adaptive negation. Our comprehensive experimental results show that our method successfully mitigates ambiguity in latent diffusion inverse solvers, enhancing their effectiveness and accuracy.
*유튜브 스트리밍 예정입니다.
-
일시: 2024.2.22.(목), 14:00~16:00
-
장소: 판교 테크노밸리 산업수학혁신센터 세미나실
- 경기 성남시 수정구 대왕판교로 815, 기업지원허브 231호 국가수리과학연구소
- 무료주차는 2시간 지원됩니다.
-
발표자: 예종철 교수(카이스트)
-
주요내용: ENLARGING THE CAPABILITY OF DIFFUSION INVERSE SOLVERS BY GUIDANCE
The recent advent of diffusion models has led to significant progress in solving inverse problems, leveraging these models as effective generative priors. Nonetheless, challenges related to the ill-posed nature of such problems remain, such as 3D extension and overcoming inherent ambiguities in measurements. In this talk, we introduce strategies to address these issues. First, to enable 3D extension using only 2D diffusion models, we propose a novel approach using two perpendicular pre-trained 2D diffusion models which guides each solver to solve the 3D inverse problem. Specifically, by modeling the 3D data distribution as a product of 2D distributions sliced in different directions, our method effectively addresses the curse of dimensionality from the image guidance from the perpendicular direction. Second, drawing inspiration from the human ability to resolve visual ambiguities through perceptual biases, we introduce a novel latent diffusion inverse solver by incorporating guidance by text prompts. Specifically, our method applies the textual deion of the preconception of the solution during the reverse sampling phase, of which deion is dynamically reinforced through null-text optimization for adaptive negation. Our comprehensive experimental results show that our method successfully mitigates ambiguity in latent diffusion inverse solvers, enhancing their effectiveness and accuracy.
*유튜브 스트리밍 예정입니다.
-
일시: 2024.2.22.(목), 14:00~16:00
-
장소: 판교 테크노밸리 산업수학혁신센터 세미나실
- 경기 성남시 수정구 대왕판교로 815, 기업지원허브 231호 국가수리과학연구소
- 무료주차는 2시간 지원됩니다.
-
발표자: 예종철 교수(카이스트)
-
주요내용: ENLARGING THE CAPABILITY OF DIFFUSION INVERSE SOLVERS BY GUIDANCE
The recent advent of diffusion models has led to significant progress in solving inverse problems, leveraging these models as effective generative priors. Nonetheless, challenges related to the ill-posed nature of such problems remain, such as 3D extension and overcoming inherent ambiguities in measurements. In this talk, we introduce strategies to address these issues. First, to enable 3D extension using only 2D diffusion models, we propose a novel approach using two perpendicular pre-trained 2D diffusion models which guides each solver to solve the 3D inverse problem. Specifically, by modeling the 3D data distribution as a product of 2D distributions sliced in different directions, our method effectively addresses the curse of dimensionality from the image guidance from the perpendicular direction. Second, drawing inspiration from the human ability to resolve visual ambiguities through perceptual biases, we introduce a novel latent diffusion inverse solver by incorporating guidance by text prompts. Specifically, our method applies the textual deion of the preconception of the solution during the reverse sampling phase, of which deion is dynamically reinforced through null-text optimization for adaptive negation. Our comprehensive experimental results show that our method successfully mitigates ambiguity in latent diffusion inverse solvers, enhancing their effectiveness and accuracy.
*유튜브 스트리밍 예정입니다.
자세히보기
