The image showcases a scientific poster presentation titled "Reconstruction via Diffusion", on display at what appears to be a conference or academic event under a "Highlight" section. The poster presents research work related to motion reconstruction technology and is authored by a group of researchers including M. Chadlecek, Siyu Tang, and Federica Bogo. The organizations involved in the research are ETH Zürich, the Visual Computing Lab (VLG), and Meta, with a mention of CVPR (Conference on Computer Vision and Pattern Recognition) 2023.

The content of the poster includes descriptions of methodologies and experiments related to global and local motion diffusion, highlighting the use of a neural network called TrajNet to improve motion plausibility. The experiments are shown through various figures and tables, displaying comparisons and results, such as the performance on different datasets and visual examples of the methodology. The section discussing the physical plausibility of the motions includes visual cues indicating the improvement of motion plausibility, and relevant metrics are provided in a tabular format.

Moreover, the poster features various visual elements, including diagrams, charts, and annotated graphs to illustrate the concepts and results comprehensively. The background of the image indicates that the event is well-lit with ceiling-mounted lights, and the setting is professional, likely with other research presentations around.
Text transcribed from the image:
Highlight
nstruction via Diffusion ETH Zürich 00 Meta
adlecek?, Siyu Tang', Federica Bogo²
fusing Global and Local Motion
global trajectory
local body pose
Ro=DR(Rt, t, CR)
(Ro, Po) = Dp((Ro, Pt), t, cp)
Inference iteration = 1
MPOP
MROR
Pt
PoseNet
Pov
康
VLG
Training on: AMASS
Computer Vision
and Learning
Croup
CVPR
SEATTLE, WA
Experiments
Test on: AMASS (synthetic noise + occlusions), PROX (RGBD/RGB), EgoBody (RGB)
Evaluation metrics:
Accuracy: MPJPE
Physical plausibility: acceleration + foot skating + foot-floor penetration
46.96
Method
R
R₁
GMPJPE
-vis -occ -all
VPoser-t 33.0 242.6 109.2 0.219
HuMor [67] 42.4 167.9 88.0 0.68 0.230
MDM++ 36.2 71.9 49.2 0.94 0.102
Ours 21.8 57.4 34.8 0.95 0.078
Contt Skat
RGB-D
RGB
1.8
1.9
Method Skating Accel Dist! Skating! Accel Dist
LEMO [100] 0.176
HuMoR [67] 0.117
PhaseMP [72]
Ours
0.038 1.8
34.22
54.76 0.139 23 35.41
0.180 1.8
3.36 0.116 22 9.73
TrajNet
Results on PROX:
No trajectory-pose correlation
→ foot skating
Results on AMASS:
182
>30% improvement over accuracy >67% (RGB-D)/>17% (RGB) improvement over foot skating
上海科技大学
University of
Zurich
Motivation
An N-Poir
e events gented by a 10 le and pr mdp fron Mi
cover partal Inear velochy and I same with a
but inear soles Applinga soliny w
for these part stationer
Contributions
1. Al ser bra ut semide
tens, this her the goonie
2.A10of angle bet ne praneration the ingred
unec ability ting der
14Monctond precin and stone de
anted by the ne
Agonyingined each se
What is an event camera?
Messaan of andra briges durs et
Advantages high temporal restored to b
power consumption, hippie ban
Multiple Solutions
The proposed soler tuft of
One my respond to floping ang
The second compond to fping the edito
Dandipue by checking the
Characte
ling Global Motion Reconstruction
ajNet with local body pose
global motion at inference time
Inference iteration > 1
TrajControl
Pt
PoseNet
Po
ME
Po
R-
TrajNet
RGB
1114
Skating
0.116
0.165
||Accel↓
→ TrajControl improves motion plausibility
2.2
Input
2.7
on PROX dataset
HUMOR
Ours
GT
HMR
30x times faster than HuMoR during inference!