From b888f899f37f3cdf098c66db9829f859ffc84ebc Mon Sep 17 00:00:00 2001 From: liwenssss <573014453@qq.com> Date: Mon, 2 Sep 2024 23:56:20 +0800 Subject: [PATCH] fix type errors --- en/index.html | 2 +- en/projects_2Dshape.html | 5 ++--- projects_2Dshape.html | 1 + 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/en/index.html b/en/index.html index 70ab8bd0..d7639394 100644 --- a/en/index.html +++ b/en/index.html @@ -143,7 +143,7 @@

About the Lab.

News

-

  • 2024.05: One paper accepted by TVCG. +
  • 2024.08: One paper accepted by TVCG.
  • 2024.08: One paper accepted by Pacific Graphics 2024.
  • 2024.05: Congrats to JIANG Weina, HE Tao and MO Haoran, who successfully defended their PhD theses!
  • 2024.05: One paper accepted by TMM. diff --git a/en/projects_2Dshape.html b/en/projects_2Dshape.html index ee203327..f39ffc4e 100644 --- a/en/projects_2Dshape.html +++ b/en/projects_2Dshape.html @@ -381,7 +381,7 @@

    Controllable Anime Image Editing via Probability of Attribute Ta Zhenghao Song, Haoran Mo, and Chengying Gao*

    - 简介： + Intro: Editing anime images via probabilities of attribute tags allows controlling the degree of the manipulation in an intuitive and convenient manner. Existing methods fall short in the progressive modification and preservation of unintended regions in the input image. We propose a controllable anime image editing framework based on adjusting the tag probabilities, in which a probability encoding network (PEN) is developed to encode the probabilities into features that capture continuous characteristic of the probabilities. Thus, the encoded features are able to direct the generative process of a pre-trained diffusion model and facilitate the linear manipulation. We also introduce a local editing module that automatically identifies the intended regions and constrains the edits to be applied to those regions only, which preserves the others unchanged. Comprehensive comparisons with existing methods indicate the effectiveness of our framework in both one-shot and linear editing modes. Results in additional applications further demonstrate the generalization ability of our approach.
    @@ -727,7 +727,6 @@

    Efficient Integration of Neural Representations for Dynamic Hum - -
    @@ -745,10 +744,10 @@

    DanceComposer: Dance-to-Music Generation Using a Progressive Con IEEE Transactions on Multimedia (TMM, 2024)  (中科院 1区/CCF-B)
    [Paper] +

    diff --git a/projects_2Dshape.html b/projects_2Dshape.html index 04df86e5..85085f55 100644 --- a/projects_2Dshape.html +++ b/projects_2Dshape.html @@ -750,6 +750,7 @@

    Efficient Integration of Neural Representations for Dynamic Hum IEEE Transactions on Visualization and Computer Graphics (TVCG, 2024)  (中科院 1区/CCF-A)
    [论文] +