Skip to content

Commit

Permalink
fix : fix thr url of imgs
Browse files Browse the repository at this point in the history
  • Loading branch information
@Gy920
Gy920 committed Feb 8, 2024
1 parent bd37a14 commit d13d948
Showing 1 changed file with 13 additions and 13 deletions.
26 changes: 13 additions & 13 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ <h4>Abstract</h4>
<h6 style="color:#8899a5" class="text-left">
We propose <strong>MASSTAR</strong>, a <strong>m</strong>ulti-modal l<strong>a</strong>rge-scale <strong>s</strong>cene dataset with a ver<strong>s</strong>atile <strong>t</strong>oolchain for surf<strong>a</strong>ce p<strong>r</strong>ediction and completion.
</h6>
<img src="assets/imgs/head_new.jpg" alt="Overview" width="70%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/head_new.jpg" alt="Overview" width="70%">
<!-- <video width="100%" playsinline="" autoplay="autoplay" loop="loop" preload="" muted="">
<source src="video/teaser.mp4" type="video/mp4">
</video> -->
Expand Down Expand Up @@ -120,7 +120,7 @@ <h4>Multi-modal Dataset Generation Toolchain</h4>
<h5 class="text-center">
A. 3D Scene Segmentation
</h5>
<img src="assets/imgs/sam_new.jpg" alt="Overview" width="75%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/sam_new.jpg" alt="Overview" width="75%">
<br><br>
<p class="text-left">
An Overview of 3D Raw Data Segmentation. Initially, we generate the depth image and RGB image by rendering a bird's-eye view of the scene. Users have the option to employ SAM for segmenting top-view images through manual selection or fully automated methods. Subsequently, the 3D model is sliced using Blender Python, and CLIP is utilized to filter out non-architectural categories.
Expand All @@ -130,7 +130,7 @@ <h5 class="text-center">
<h5 class="text-center">
B. Images Rendering
</h5>
<img src="assets/imgs/render.jpg" alt="Overview" width="60%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/render.jpg" alt="Overview" width="60%">
<br><br>
<p class="text-left">
An example of the image rendering part of the toolchain. We offer the random mode (left) and trajectory mode (right) for users to choose from.
Expand All @@ -139,7 +139,7 @@ <h5 class="text-center">
<h5 class="text-center">
C. Descriptive Texts
</h5>
<img src="assets/imgs/text.jpg" alt="Overview" width="60%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/text.jpg" alt="Overview" width="60%">
<br><br>
<p class="text-left">
An example of the descriptive text render part of toolchain. we utilize BLIP to perform zero-shot image-to-text generation.
Expand Down Expand Up @@ -177,13 +177,13 @@ <h4>Example of dataset</h4>
<!-- <h6 style="color:#8899a5" class="text-left">
We propose MASSTAR, a multi-modal large-scale scene dataset with a versatile toolchain for surface prediction and completion.
</h6> -->
<img src="assets/imgs/rotation_new.gif" alt="ablation-representation" width="80%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/rotation_new.gif" alt="ablation-representation" width="80%">
<!-- <br> -->
<!-- <p class="text-center">
result
</p> -->
<!-- <br> -->
<!-- <img src="assets/imgs/table.png" alt="ablation-representation" width="100%">
<!-- <img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/table.png" alt="ablation-representation" width="100%">
<p class="text-center">
the ouput .
</p>
Expand All @@ -208,7 +208,7 @@ <h4>Surface Completion Benchmark</h4>
<h6 style="color:#8899a5" class="text-left">
We conducted a comparative analysis of three surface prediction and completion algorithms, including SPM, PCN, and XMFnet.
</h6>
<img src="assets/imgs/result.gif" alt="ablation-representation" width="90%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/result.gif" alt="ablation-representation" width="90%">
<!-- <br>
<p class="text-center">
result
Expand All @@ -217,20 +217,20 @@ <h6 style="color:#8899a5" class="text-left">
<!-- <div style="display: flex;">
<div style="display: flex; flex-direction: column;flex-direction: column;
justify-content: space-between;">
<img src="assets/imgs/infer_time.png" alt="ablation-representation" width="90%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/infer_time.png" alt="ablation-representation" width="90%">
<h8 class="text-center">
Time Efficiency and Resource Consumption of Each Method
</h8>
</div>
<div style="display: flex; flex-direction: column;flex-direction: column;
justify-content: space-between;">
<img src="assets/imgs/eval.png" alt="ablation-representation" width="90%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/eval.png" alt="ablation-representation" width="90%">
<h7 class="text-center">
The Quality of Prediction Result of Each Method
</h7>
</div>
</div> -->
<!-- <img src="assets/imgs/table.png" alt="ablation-representation" width="100%">
<!-- <img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/table.png" alt="ablation-representation" width="100%">
<p class="text-center">
the ouput .
</p>
Expand All @@ -252,7 +252,7 @@ <h2>Benchmark results</h2>
<hr style="margin-top:0px">
<video width="100%" playsinline="" autoplay="autoplay" loop="loop" preload="" muted="">
<source src="video/more_gso.mp4" type="video/mp4">
<img src="assets/imgs/result2.jpg" alt="ablation-representation" width="100%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/result2.jpg" alt="ablation-representation" width="100%">
</video>
<p class="text-center">
More results from GSO dataset.
Expand All @@ -277,14 +277,14 @@ <h2>Benchmark results</h2>
<div class="col-12 text-center">
<h2>Ablation</h2>
<hr style="margin-top:0px">
<img src="assets/imgs/result2.jpg" alt="ablation-representation" width="100%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/result2.jpg" alt="ablation-representation" width="100%">
<p class="text-center">
Qualitative comparison between different 3D representations: (1) naive generalizable 3D Gaussian (3DG), (2) Triplane-NeRF and (3) Triplane-Guassian.
</p>
<video width="100%" playsinline="" autoplay="autoplay" loop="loop" preload="" muted="">
<source src="video/ab.mp4" type="video/mp4">
</video>
<img src="assets/imgs/plot_result2.jpg" alt="ablation-method" width="100%">
<img src="https://raw.githubusercontent.com/SYSU-STAR/MASSTAR/gh_page/assets/imgs/plot_result2.jpg" alt="ablation-method" width="100%">
<p class="text-center">
Ablation experiments to assess the effect of Projection-aware Condition (P.C.) and Geometry-aware Encoding (G.E.).
</p>
Expand Down

0 comments on commit d13d948

Please sign in to comment.