diff --git a/.gitattributes b/.gitattributes index e3cf4186fbf2ac06524ae6255b9a7c58bf6e1892..e5b5961d385b4642f81fdd06cfdadc25d2293d30 100644 --- a/.gitattributes +++ b/.gitattributes @@ -46,4 +46,3 @@ static/videos/shiba.mp4 filter=lfs diff=lfs merge=lfs -text static/videos/steve.mp4 filter=lfs diff=lfs merge=lfs -text static/videos/teaser.mp4 filter=lfs diff=lfs merge=lfs -text static/videos/toby.mp4 filter=lfs diff=lfs merge=lfs -text -*.png filter=lfs diff=lfs merge=lfs -text diff --git a/index.html b/index.html index ab8647f1aca984e211946eea5b53b30342653186..88951116f7ed81764f0d75616b9f4c60892b9a30 100644 --- a/index.html +++ b/index.html @@ -2,170 +2,29 @@ - - + + - RTC Experiments: Flow Matching Steps & Sigma Analysis + Nerfies: Deformable Neural Radiance Fields + + - + + - + - - + + + @@ -174,10 +33,86 @@
-

Real-Time Chunking Experiments

-

Flow Matching Steps & Sigma_d Parameter Analysis

+

Nerfies: Deformable Neural Radiance Fields

+ +
- LeRobot RTC Integration Tests + 1University of Washington, + 2Google Research +
+ +
@@ -185,305 +120,316 @@
-
+
-
-

Experiment Overview

-
-

- This page presents comprehensive results from Real-Time Chunking (RTC) experiments across different models, - flow matching steps, and sigma_d values. The experiments demonstrate how these parameters affect the - denoising process and final action predictions. -

-

- Models tested: PI0.5, SmolVLA
- Flow matching steps: 10, 20, 50, 100
- Sigma_d values: 0.1, 0.2, 0.5, 0.8, 1.0, 1.2, 1.5
- Modes: Classical RTC (fulltrajectory=false), Full Trajectory (fulltrajectory=true) -

-

- Classical RTC: Uses RTC guidance during denoising with chunked trajectory processing.
- Full Trajectory: Processes the complete trajectory without chunking. -

-
+
+ +

+ Nerfies turns selfie videos from your phone into + free-viewpoint + portraits. +

+
+
- - - -