From 26c7885109d08dfec77f02e9abf9361e8377747d Mon Sep 17 00:00:00 2001
From: Zhihang Zhong <zzh.tech@gmail.com>
Date: Thu, 30 Nov 2023 12:47:09 +0800
Subject: [PATCH] add interface of video inference

---
 .gitignore      |  3 ++-
 docs/index.html | 11 ++++++++---
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/.gitignore b/.gitignore
index 4d0e9d0..56c5bbe 100644
--- a/.gitignore
+++ b/.gitignore
@@ -162,4 +162,5 @@ cython_debug/
 demo/
 models/
 results/
-webapp/
\ No newline at end of file
+webapp/
+checkpoints/
\ No newline at end of file
diff --git a/docs/index.html b/docs/index.html
index f1c4523..283561f 100755
--- a/docs/index.html
+++ b/docs/index.html
@@ -314,7 +314,11 @@ <h2 class="title is-3">Manipulated interpolation of anything</h2>
                                     <b>
                                         Additionally, our strategies enable temporal manipulation of each object
                                         independently during the inference stage, offering a novel tool for video
-                                        editing tasks like re-timing.
+                                        editing tasks like re-timing. <u
+                                            style="color: black; text-decoration: underline black;">Our <a
+                                            href="http://ai4sports.opengvlab.com"
+                                            target="_blank">APP</a> also
+                                        supports video as an input to classic video frame interpolation.</u>
                                     </b>
                                 </em>
                             </p>
@@ -490,7 +494,8 @@ <h4 class="title is-5">Editable interpolation</h4>
             <p>
                 <b>Beyond using a uniform index map like time indexing, we can also take advantage of the 2D editable
                     nature of path distance indexing to implement editable frame interpolation techniques.</b>
-                Initially, we can obtain masks for objects of interest using the Segment Anything Model (SAM) [5]. We then
+                Initially, we can obtain masks for objects of interest using the Segment Anything Model (SAM) [5]. We
+                then
                 customize the path distance curves for different object regions to achieve manipulated interpolation of
                 anything.
             </p>
@@ -513,7 +518,7 @@ <h2 class="title is-3">Ending</h2>
                 This work presents the next generation of video frame interpolation technology, aiming to inspire
                 readers and contribute to fields like video enhancement, editing, and generation! 🔥🔥🔥
                 <br>
-                Welcome to star <a href="https://github.com/zzh-tech/InterpAny-Clearer">this project</a>
+                Welcome to &#127775; <a href="https://github.com/zzh-tech/InterpAny-Clearer">this project</a>
                 and follow <a href="https://github.com/zzh-tech">the author's GitHub</a>～
             </p>
         </div>