Diffuse-CLoC:
Guided Diffusion for Physics-based
Character Look-ahead Control
2025. 07. 18.
SEOUL NATIONAL UNIVERSITY
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
(Bldg.302 #312-1)
WONJEONG SEO
Review | SIGGRAPH ’25 (TOG)
2
0. LINK
https://diffusecloc.github.io/website/
3
1. GOAL
Physically Steerable Character Control for Zero-Shot Tasks
Train Diffusion Model
Condition
Guidance
Unseen Tasks
w/o retraining, high-level controller
4
2. RELATED WORKS
Physics-based Control using Diffusion Model
steerability↓
fine-tuning (per task)
depends on kinematic trajectory (tracking)
5
2. RELATED WORKS
Physics-based Control using Diffusion Model
steerability↓
fine-tuning (per task)
depends on kinematic trajectory (tracking)
6
3. KEY CONCEPTS
Perform unseen task w/o high-level controller or retraining NN
7
4. FRAMEWORK
Joint Distribution Transformer Diffusion Model
Training Step]
8
4. FRAMEWORK
Joint Distribution Transformer Diffusion Model
Inference Step]
Backward process
9
4. FRAMEWORK
Cost Functions
Static obstacle avoidance
Dynamic obstacle avoidance
10
4. FRAMEWORK
Attention for States and Actions
state -> state (prevent compromising kinematic information)
action -> causal state/action pair (preserve consistency)
11
4. FRAMEWORK
Rolling Inference Scheme
12
5. RESULTS
13
5. RESULTS
14
5. RESULTS
15
5. RESULTS