Skip to content

[SIGGRAPH Asia 2026] 4DAnyone: Create Anyone in 4D from a Casual Monocular Video

Reduce README figure width

krahets20cff246dad9
diff --git a/README.md b/README.md
index 3a49721..d33ee2f 100644
--- a/README.md
+++ b/README.md
@@ -42,7 +42,7 @@ python inference.py \
--views_per_layer 6
```
-<p align="left"><img src="docs/assets/inference-6-views.jpg" width="800" alt="Six evenly spaced target cameras on one full orbit"></p>
+<p align="left"><img src="docs/assets/inference-6-views.jpg" width="600" alt="Six evenly spaced target cameras on one full orbit"></p>
### 24-view full orbit
@@ -54,7 +54,7 @@ python inference.py \
--views_per_layer 24
```
-<p align="left"><img src="docs/assets/inference-24-views.jpg" width="800" alt="Twenty-four evenly spaced target cameras on one full orbit"></p>
+<p align="left"><img src="docs/assets/inference-24-views.jpg" width="600" alt="Twenty-four evenly spaced target cameras on one full orbit"></p>
### 48-view, three pitch layers
@@ -66,7 +66,7 @@ python inference.py \
--views_per_layer 16 --layer_pitches '[-10,15,35]'
```
-<p align="left"><img src="docs/assets/inference-48-views-3-layers.jpg" width="800" alt="Forty-eight target cameras arranged over three pitch layers"></p>
+<p align="left"><img src="docs/assets/inference-48-views-3-layers.jpg" width="600" alt="Forty-eight target cameras arranged over three pitch layers"></p>
### 8-view frontal arc
@@ -78,7 +78,7 @@ python inference.py \
--views_per_layer 8 --start_yaw -90 --yaw_span 180
```
-<p align="left"><img src="docs/assets/inference-8-views-front-180.jpg" width="800" alt="Eight target cameras distributed over the frontal 180-degree arc"></p>
+<p align="left"><img src="docs/assets/inference-8-views-front-180.jpg" width="600" alt="Eight target cameras distributed over the frontal 180-degree arc"></p>
### Camera layout options