Otmar Hilliges @OHilliges Twitter profile

Last Seen Profiles

@cromaaa_

@hjmatey

@rxubah

@denverbitcoin

@ErikStolz1

@Eric_Sadin

@ixo9i

@kirwoo_

@dabong_CM

@WorldLiverDay

@tholaadeloye

@stowerkstatt

@janndalower459

@iVivekSinghVns

@LooksmaxMe

@BingzhangC

@2023sydneys

@marrathon

@ledgerkeele59

@TedTalksDrag

@FrancisRoc78288

@Bearwaves

@chefmuto

@jihunmin__alt

@theterras

@jandakembangstw

@DEREKMNEWTON1

@CaseyboyWMMR

@9Dnnn

@stw_pdg

@andreafuerteess

@J_DeVitis

@MGupta4Bharat

@marksalcido

@Ellametcalf1

@nsthcssn

Otmar Hilliges

@OHilliges

5 months

In 2022, I finished 2 half marathons, 2 MTB races, and my computer vision research group was firing on all cylinders. In 2023 our lives were turned upside down by severe #LongCovid and #MECFS . 1/

155

308

1K

Otmar Hilliges

@OHilliges

11 months

Some of you may have seen this already 😀 I'm still very excited about Vid2Avatar which we will present at #CVPR2023 this week. We propose a method to reconstruct detailed 3D avatars from monocular in the wild videos via self-supervised scene decomposition. 🧵👇 1/

21

249

1K

Otmar Hilliges

@OHilliges

1 year

Warning: personal and emotional thread. Today is #MEAwarenessDay and we are heartbroken 💔. Our smart, athletic, ball-of-energy 10 year old is now bedridden and unable to stand or walk since January due to #LongCOVID and #MECFS . #LongCovidKids 👇🧵 1/

34

332

900

Otmar Hilliges

@OHilliges

5 months

I am painfully aware that we are only two of 60+ million patients with #LongCovid ( #pwLC ) and tens of millions with #MECFS ( #pwME ). Yet despite these numbers, there has been zero public research funding and hence no cure, no therapy, or quality-of-life care. 4/

9

55

376

Otmar Hilliges

@OHilliges

5 months

To make matters worse, our younger son, who also has #LongCovid , has been unable to stand or walk since January, and has been too sick to attend school in over a year. #LongCovidKids 3/

8

63

343

Otmar Hilliges

@OHilliges

5 months

If you want to give some hope to people suffering from these conditions, please consider donating to any of the research foundations below. They do amazing work. You can also help by spreading the word. @polybioRF @OpenMedF @MECFSResearch #chronicillness #nichtgenesen

9

51

327

Otmar Hilliges

@OHilliges

5 months

Today I spend nearly 24/7 lying in bed in a quiet, darkened room. Even the smallest activity, such as eating, can cause me to crash (a rapid worsening of symptoms). 2/

8

36

287

Otmar Hilliges

@OHilliges

1 year

Sad and infuriating reality: 3 years in, and most medical staff remain ill-informed or even unwilling to acknowledge #LongCOVID . Grateful for the few doctors and therapists like @SusScro58355800 who are trying to help. It's time for a change. 4/

4

23

164

Otmar Hilliges

@OHilliges

1 year

Last summer, months after Covid he repeatedly developed headaches and felt ill then suddenly got better. Specialist after specialist dismissed his symptoms, urging him to return to school and exercise. Little did we know, this triggered #PEM , worsening his condition. 2/

2

29

160

Otmar Hilliges

@OHilliges

1 year

In our latest TPAMI paper we introduce FastSNARF! An efficient deformer for non-rigid shapes, represented as neural fields (SDF, NeRF, etc.). It's a 1:1 replacement to our previous work, SNARF but 150x faster! 🚀⚡ #FastSNARF #NeuralFields #NeuralAvatars 🧵👇 1/6

AIT Lab

@ait_eth

3 years

#ICCV21 Session 9 “SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes” by @XuChen71058062 , Yufeng, @Michael_J_Black , Otmar, Andreas @AutoVisionGroup homepage: code: paper:

1

5

15

1

30

152

Otmar Hilliges

@OHilliges

1 year

It saddens and embarrasses me how comparatively easy it is to secure funding for my own research in computer vision, while in #MECFS researchers struggle to obtain support. May is #MEAwarenessMonth - let’s push for equitable funding and resources. 6/

1

25

151

Otmar Hilliges

@OHilliges

1 year

Awareness for #PEM , #LongCOVID , and #MECFS is crucial to prevent such devastating outcomes. 3/

1

16

149

Otmar Hilliges

@OHilliges

2 years

One step closer to realistic virtual humans: with gDNA we propose a method that generates diverse 3D virtual humans appearing in varied clothing and under full pose control! #CVPR2022 Paper: Video:

2

19

150

Otmar Hilliges

@OHilliges

2 years

Our latest toy is finally online 🎉🚀 Super excited about the upcoming computer vision and graphics research on neural avatars, human state estimation and much more leveraging one of the most advanced volumetric video capture studios in academia! @ait_eth , @mapo1 , @MarkusGross63

ETH CS Department

@CSatETH

2 years

Great opening of the new state-of-the-art volumetric video capture facility to create #4Davatars with exciting fields of application, e.g. in transportation, aging society or health care. @mapo1 @OHilliges @MarkusGross63 @ETH_en

2

15

86

1

23

147

Otmar Hilliges

@OHilliges

2 years

Need to scan and animate yourself? @YufengZzzz will present I M Avatar at #CVPR2022 (oral) - which learns implicit head avatars from monocular videos via correspondence search and differentiable ray-marching. Paper: Project:

2

19

146

Otmar Hilliges

@OHilliges

1 year

Even worse: #MECFS , known since the 50s, yet still no substantial funding or approved medications. With an estimated 17.5 million sufferers pre-pandemic, this is an urgent crisis. It's time to invest real money into basic and translational research. Lives are at stake. 5/

2

22

142

Otmar Hilliges

@OHilliges

1 year

Please help to spread understanding and support for millions - many of them kids and young adults - suffering from these debilitating conditions. Raising awareness is a first step towards better care and research. 💙. #LongCovidKids #LongCovid #MECFS 7/7

9

25

136

Otmar Hilliges

@OHilliges

2 years

Yufeng ( @YufengZzzz ) is about to present our paper on learning implicit morphable head avatars from videos at #CVPR2022 (oral: Image & Video Synthesis Session, 1:30pm). Sadly I can't be there in person but don't fret, Yufeng can still make my Avatar say cheeky things 😆

5

23

137

Otmar Hilliges

@OHilliges

11 months

Vid2Avatar #CVPR2023 : @ChenGuo96 , Tianjian Jiang, @XuChen71058062 , Jie Song and me. More cool demos: Code: Paper: 7/7

3

17

121

Otmar Hilliges

@OHilliges

2 years

For AIs to reason about human interaction with the world, we need generative models that can imagine a plausible future. In our upcoming #CVPR2022 paper, we introduce D-Grasp, an RL-based method that generates physically plausible grasp sequences.

2

16

112

Otmar Hilliges

@OHilliges

11 months

Implicit surfaces are great to reconstruct 3D humans. However, editing is hard because the geometry is represented by a single continuous function. In our upcoming #CVPR2023 paper, we overcome this by combining the advantages of explicit and implicit representations. 🧵👇

1

11

82

Otmar Hilliges

@OHilliges

2 years

The application window for the ETH-CLS PhD program is now open: This is a great opportunity to do cutting-edge research in 3D computer vision and be co-supervised by fantastic advisors at ETH and the MPI ( @Michael_J_Black , @JustusThies ).

How to Apply | Max Planck ETH Center for Learning Systems

learning-systems.org

1

23

80

Otmar Hilliges

@OHilliges

11 months

Just in time for #CVPR2023 we release Hi4D, a dataset of closely interacting humans in 4D, including 4D textured geometry, multi-view RGB images, registered parametric models, instance segmentation masks in 2D & 3D, and vertex-level contact annotations. 🧵👇

2

9

73

Otmar Hilliges

@OHilliges

7 months

Excited to share our latest collaboration between @ait_eth and @GoogleARVR on very high-resolution face synthesis. @mc_buehler will present this work at #ICCV2023 next week. More info 👇

Marcel Bühler

@mc_buehler

7 months

Introducing "Preface: A Data-driven Volumetric Prior for Few-shot Ultra High-resolution Face Synthesis". TL;DR: Novel views of faces at ultra-high 4K resolution from very few input images. @GoogleARVR @ETH_en @ait_eth #ICCV2023 . See thread below.

8

56

195

0

4

67

Otmar Hilliges

@OHilliges

11 months

For digital humans to come alive they need to be expressive! In our #CVPR2023 paper, X-Avatar, we propose an implicit human avatar model capable of capturing human body poses, hand gestures, facial expressions, and appearance 🕺🏻 1/ 🧵👇

2

14

63

Otmar Hilliges

@OHilliges

11 months

We are excited to announce the HANDS'23 workshop challenge () with AssemblyHands and ARCTIC at #ICCV2023 ! The challenge focuses on hand pose estimation and articulated hand-object reconstruction (Deadline: September 15). See 🧵 for more details.

1

19

54

Otmar Hilliges

@OHilliges

11 months

Building on Fast-SNARF, we take another important step towards real-time neural avatars. Our latest #CVPR paper InstantAvatar proposes a method to reconstruct animatable full-body avatars from a monocular video in less than 60 seconds. ⚡️ #NeuralAvatars #DigitalHumans 🧵👇 1/

Otmar Hilliges

@OHilliges

1 year

In our latest TPAMI paper we introduce FastSNARF! An efficient deformer for non-rigid shapes, represented as neural fields (SDF, NeRF, etc.). It's a 1:1 replacement to our previous work, SNARF but 150x faster! 🚀⚡ #FastSNARF #NeuralFields #NeuralAvatars 🧵👇 1/6

1

30

152

2

13

51

Otmar Hilliges

@OHilliges

7 months

AG3D is an important step on our quest towards fully generative models of realistic 3D humans. It is learned entirely from 2D image collections and requires no 3D supervision. To be presented at #ICCV2023 .

Zijian Dong

@dong_zijian

7 months

**Introducing AG3D**: Learning to Generate 3D Avatars from 2D Image Collections. 🔗Full Info: Catch our presentation at @ICCVConference in Paris! 🗓️Date: Thursday 🕰️Time: 14:30 - 16:30 📌Paper ID: 1836 📍Location: Room "Foyer Sud" 088 🔽Details Below:

2

44

146

1

6

51

Otmar Hilliges

@OHilliges

1 year

Last night @emreaksan has been awarded the Fritz-Kutter award for his outstanding PhD thesis. Congratulations! Very well deserved Emre! Proud advisor moment.

7

2

51

Otmar Hilliges

@OHilliges

8 months

Checkout our new dataset EMDB for 3D human pose estimation in uncontrolled outdoor environments 👇. To appear at #ICCV2023

AIT Lab

@ait_eth

8 months

We are excited to share EMDB, a novel dataset of 3D human poses for in-the-wild monocular videos, including global trajectories. Data and toolkit code is now available. More details in the thread below. Project Page:

1

19

51

0

8

50

Otmar Hilliges

@OHilliges

2 years

I'm honored to have been awarded an ERC consolidator grant! Looking forward to working with my superstar students @ait_eth on next gen computer vision for collaborative AIs.

ERC Consolidator Grants for Otmar Hilliges and Martin Vechev

inf.ethz.ch

2

5

50

Otmar Hilliges

@OHilliges

2 years

@ait_eth The implication: papers are for reading, discussing, ideating - not for counting. To all the junior folks: focus on doing good work, the rest will follow.

0

7

48

Otmar Hilliges

@OHilliges

1 year

Excited to share our upcoming #CVPR2023 paper #PointAvatar that leverages learned, deformable point clouds to create high fidelity 3D facial avatars efficiently from video. 👇

Michael Black

@Michael_J_Black

1 year

Efficiently create accurate and realistic 3D facial avatars that can be animated and lit in new environments. Recent implicit shape models look good but are slow to learn and render. Our #PointAvatar method is high quality and more efficient. Appearing at #CVPR2023 . (1/9)

1

37

178

0

4

47

Otmar Hilliges

@OHilliges

2 years

Excited to be in Prague for #3dv2022 . First in person conference in close to three years.

1

3

41

Otmar Hilliges

@OHilliges

11 months

Our method generalizes to diverse human shapes, garment styles, and facial features even under challenging poses and complicated environments without requiring any external segmentation. 5/

1

4

41

Otmar Hilliges

@OHilliges

2 years

Congratulations to all #CVPR2022 authors! I'm happy to announce that we also got X/Y papers accepted. Fantastic work by my very talented students @ait_eth lab and great collaborators. Stay tuned.

1

2

41

Otmar Hilliges

@OHilliges

2 years

We're looking for ELLIS PhD candidates at ETH Zurich @ait_eth . Topics in human-centric 3D computer vision include 3D pose, shape and appearance estimation and underlying methods such as neural fields, 3D generative models and more.

0

6

40

Otmar Hilliges

@OHilliges

11 months

I would have loved to go to #CVPR2023 this year. Alas our family’s health situation does not allow for that. For all of you attending: enjoy, stay healthy and go chat my students and postdocs (even if less than 50% of the authors from @ait_eth got a visa).

2

4

39

Otmar Hilliges

@OHilliges

2 years

On the way to the Swiss computer vision faculty retreat. First physical event since iccv ‘19? Exciting! #Gstaad

2

0

39

Otmar Hilliges

@OHilliges

2 years

Last year we introduced a principled method to learn articulated neural surfaces from scans (). This year at #CVPR2022 we show how to learn personalized avatars from a single RGB-D sequence: . Great work by @dong_zijian & @ChenGuo96 !

1

9

37

Otmar Hilliges

@OHilliges

2 years

Hand pose estimation often ignores temporal information. In TempCLR, we introduce a time-contrastive learning objective that significantly improves hand pose reconstruction from in-the-wild videos and that improves cross-dataset generalization. #3dv2022 #handposeestimation

1

11

34

Otmar Hilliges

@OHilliges

11 months

Thursday poster presentations from @ait_eth and friends. 👇 AM - X-Avatar & instant avatar:

2

0

24

Otmar Hilliges

@OHilliges

11 months

Once reconstructed, the avatars can be animated using arbitrary input pose sequences, including pose dependent deformations. 6/

1

23

Otmar Hilliges

@OHilliges

11 months

Frau Dr. Strasser ruft im Schweizer Ärzteblatt für eine bessere Versorgung von #LongCovid und #MECFS Patienten, sowie für mehr und bessere Forschung auf! 👏🙌🙌. Der Paradigmenwechsel ist dringend nötig. @SusScro58355800

Aufruf zu einem überfälligen Paradigmenwechsel

saez.swisshealthweb.ch

1

8

24

Otmar Hilliges

@OHilliges

11 months

We show that solving the problem entirely in 3D - and forgoing the use of 2D segmentation methods - leads to better results overall. We model both the human and the background in the scene jointly, parameterized via two layered neural fields. 3/

1

0

25

Otmar Hilliges

@OHilliges

2 years

Unfortunately Xu ( @XuChen71058062 ) couldn't attain a Visa. However, his method can generate detailed and varied 3D virtual humans. How? Find out at: Poster 167b #CVPR22 ! There will be real humans - I promise 😀. @jinlongyang , @Michael_J_Black , @AutoVisionGroup

Otmar Hilliges

@OHilliges

2 years

One step closer to realistic virtual humans: with gDNA we propose a method that generates diverse 3D virtual humans appearing in varied clothing and under full pose control! #CVPR2022 Paper: Video:

2

19

150

1

4

24

Otmar Hilliges

@OHilliges

1 year

I’m proud that two members of the AIT lab @ait_eth , Marcel Bühler @mc_buehler and Xu Chen @XuChen71058062 , have been recognized as outstanding reviewers for #CVPR2023 ! I always say that if you want to receive good reviews; write good reviews.

#CVPR2024

@CVPR

1 year

We sincerely thank all reviewers, area chairs and senior area chairs who contributed their time to #CVPR2023 ! Reviewers who did an outstanding job are recognized here:

3

9

95

1

23

Otmar Hilliges

@OHilliges

2 years

I really was super excited about finally seeing everyone in person at #CVPR2022 but in the end I decided not to go this year. Why? Some of my rationale below (1/6)

1

0

20

Otmar Hilliges

@OHilliges

11 months

Phd students at @ait_eth making the best out of the visa debacle

Xu Chen

@XuChen71058062

11 months

Friends and I finally made it to @CVPR without visa!🎉 Just kidding😄We made a fun "group photo" of @ait_eth with generative fill @Adobe .Thanks @OHilliges for shooting😉Truly astonished by #GenerativeAI ! More motivation to research generative 3D human: maybe 3D selfie one day😉

1

12

70

0

16

Otmar Hilliges

@OHilliges

11 months

We formulate a global optimization over the background and canonical human model. A coarse-to-fine sampling strategy for volume rendering and novel objectives to cleanly separate the human and static background, yield detailed and robust 3D human geometry reconstructions. 4/

1

0

18

Otmar Hilliges

@OHilliges

11 months

Most existing methods rely on background segmentation in 2D. This can upper-bound the final reconstruction quality due to mislabeled pixels. 2/

1

17

Otmar Hilliges

@OHilliges

11 months

Coming up at #CVPR - hierarchical graph neural networks and physical self-supervision lead to neural garment simulation that generalizes across garments, handles varying topologies and models the dynamics of free flowing clothing. 👇

Artur Grigorev

@ArturGrigorev57

1 year

📢📢 Have been waiting for a garment modeling method, that - 👕👚👖needs just one model for all types of garments - 🥼handles changing topology (e.g. buttons) - 👗realistically models loose garments? Happy to present our #CVPR2023 paper HOOD Project:

4

21

133

0

2

15

Otmar Hilliges

@OHilliges

11 months

❄️ ARCTIC Challenge: is focussed on consistent motion reconstruction. The aim is to reconstruct 3D surfaces of two hands and of an articulated object in each video frame. Crucially, the hand-object contact must be consist to explain object articulation.

1

9

15

Otmar Hilliges

@OHilliges

11 months

@ugoerra Currently processing takes several hours but keep in mind this non-optimized research code. For quasi- real-time checkout #InstantAvatar (also at #CVPR2023 ).

1

15

Otmar Hilliges

@OHilliges

2 years

This is big news for @INSAITinstitute , Europe and Computer Vision research in the area. 👏

INSAIT Institute

@INSAITinstitute

2 years

Prof. Luc Van Gool, one of the world’s top AI and Computer Vision scientists, is joining @INSAITinstitute in Sofia. His arrival is made possible by the 6M EUR financial support provided by @SiteGround @CVPR

0

5

23

0

1

12

Otmar Hilliges

@OHilliges

11 months

Today at #CVPR contributions from the AIT lab and collaborators. 👇 AM:

1

12

Otmar Hilliges

@OHilliges

11 months

We're also excited to share a novel 3D human dataset - CustomHumans. Our dataset contains over 600 high-quality scans of humans alongside accurately registered SMPL-X parameters. 5/

1

11

Otmar Hilliges

@OHilliges

1 year

Code, paper and more is available here: Github: Paper: 3D viewer: 5/6

2

1

12

Otmar Hilliges

@OHilliges

2 years

Luckily a lot of my students will be there to present their awesome work. So go see their talks and posters and discuss with them. Already looking forward to a virtual #CVPR2022 and an in person #CVPR2023 . (6/6)

0

11

Otmar Hilliges

@OHilliges

1 year

FastSNARF enables efficient training and inference of digital 3D humans. Powered by the latest release of aitviewer @ait_eth , we stream live network outputs in quasi-realtime - and so can you! 4/6

1

3

10

Otmar Hilliges

@OHilliges

2 years

Fantastic work by @sammy_j_c (first author), @mkocab_ , @emreaksan , Jie Song and @HwangboJemin Project page: Paper: Video:

D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object...

We introduce the dynamic grasp synthesis task: given an object with a known 6D pose and a grasp reference, our goal is to generate motions that move the obje...

www.youtube.com

0

3

10

Otmar Hilliges

@OHilliges

1 year

@cjmaddison Thanks Chris. I was very saddened when I found out your suffering from post-COVID. Your outspokenness on the issue helped strengthen my resolve to share our story.

0

10

Otmar Hilliges

@OHilliges

2 years

Excited to be part of this initiative to build a new world-class AI institute in Europe. I'm happy to hire up to two doctoral students (PhDs) at @INSAITInstitute who will work closely with me and the AIT lab @ait_eth at ETH Zurich.

INSAIT Institute

@INSAITinstitute

2 years

We are excited to launch our world-class AI/CS PhD program (), the first of its kind in Eastern Europe, with @DeepMind PhD fellowships, please share :)

2

24

90

0

4

10

Otmar Hilliges

@OHilliges

2 years

PINA is a tribute to Pina Bausch; it's also the name of our method that creates personalised avatars from RGB-D videos - and makes them dance 🕺💃. Today at #CVPR2022 , Session: 4.2, Poster: 171b @dong_zijian , @ChenGuo96 , Jie Song, @AutoVisionGroup , me

Otmar Hilliges

@OHilliges

2 years

Last year we introduced a principled method to learn articulated neural surfaces from scans (). This year at #CVPR2022 we show how to learn personalized avatars from a single RGB-D sequence: . Great work by @dong_zijian & @ChenGuo96 !

1

9

37

1

2

10

Otmar Hilliges

@OHilliges

11 months

Tomorrow @sammy_j_c will present his work on vision-based hand off of objects from humans to robots at #CVPR2023 . Go see the talk and poster. 🦿 More info in the thread 👇

Sammy Joe Christen

@sammy_j_c

11 months

In our upcoming #CVPR2023 highlight paper, we propose the first framework to learn vision-based human-to-robot handovers. This task is challenging because it requires an accurate simulation of humans and a robot that can react to dynamic human movements. 🧵👇

1

4

16

0

1

8

Otmar Hilliges

@OHilliges

11 months

The reconstructed X-Avatars can be driven by motion that has been extracted from online RGB videos. 5/

1

7

Otmar Hilliges

@OHilliges

1 year

A fantastic collaboration between ETH Zurich @ait_eth , MPI-IS @MPI_IS , the University of Tuebingen @uni_tue , and NVIDIA @NVIDIA . Team: Xu @XuChen71058062 , Tianjian Jiang, Jie Song, Max Rietmann @why_maxim , Andreas Geiger @AutoVisionGroup , @Michael_J_Black , and myself! 6/6

0

7

Otmar Hilliges

@OHilliges

2 years

@ait_eth @mapo1 @MarkusGross63 Also: we're hiring post-docs and PhD students at ETH @ait_eth and INSAIT @INSAITinstitute . Come work with us on the future of human-centric computer vision.

0

1

7

Otmar Hilliges

@OHilliges

11 months

Code, paper, and dataset are now publicly accessible for research purposes! 👨‍💻Code: 📄Paper: 📊Dataset: 🎥Video: 🖼️ Poster: Come chat with us at #CVPR2023

0

2

7

Otmar Hilliges

@OHilliges

2 years

Fantastic work with Work by Andrea Ziani, @zc_alexfan , @mkocab_ and @sammy_j_c ! (first two authors contributed equally) More info and materials:

0

2

7

Otmar Hilliges

@OHilliges

11 months

Code, paper, video, and data at: Joint work by Kaiyue Shen, @ChenGuo96 , @ManuelKaufmann1 , @JuanJos , @JPCValentin , Jie Song, and myself.

0

2

5

Otmar Hilliges

@OHilliges

1 year

How? We replace the MLP and leverage a compact voxel grid to represent the skinning weight field, thanks to its inherent smoothness. Plus, we exploit the linearity of LBS to streamline computations, slashing time without compromising accuracy. 2/6

1

0

6

Otmar Hilliges

@OHilliges

2 years

Our method can also be used to correct imperfect labels (e.g., from existing datasets) or predictions from static grasp synthesis methods and even image based pose estimates.

1

2

6

Otmar Hilliges

@OHilliges

2 years

Wanting the pandemic to be over and it actually being over, sadly, is not the same thing. My social media stream was full of folks coming back with Covid from #CHI2022 (also in NOLA), some getting stuck in quarantine hotels for significant amounts of time. (2/6)

1

0

6

Otmar Hilliges

@OHilliges

2 years

Today Sammy will present our paper on learning natural and physically plausible human object interaction sequences at #CVPR22 (Session: Faces and Gestures, Poster: 181b). Do stop by. @sammy_j_c , @mkocab_ , @emreaksan , @HwangboJemin Project

Otmar Hilliges

@OHilliges

2 years

For AIs to reason about human interaction with the world, we need generative models that can imagine a plausible future. In our upcoming #CVPR2022 paper, we introduce D-Grasp, an RL-based method that generates physically plausible grasp sequences.

2

16

112

0

5

6

Otmar Hilliges

@OHilliges

2 years

Another awesome collaboration with @XuChen71058062 , @Michael_J_Black , @AutoVisionGroup

0

5

Otmar Hilliges

@OHilliges

11 months

Explore the InstantAvatar project in depth: Project page: Github: Read our paper: Joint work by Tianjian Jiang, @XuChen71058062 , Jie Song, and myself @ait_eth . 5/5

GitHub - tijiang13/InstantAvatar

Contribute to tijiang13/InstantAvatar development by creating an account on GitHub.

github.com

2

3

4

Otmar Hilliges

@OHilliges

2 years

Also don't forget to stop by during the poster session. More info: @YufengZzzz , @mc_buehler , @vfabrevaya , @Michael_J_Black

1

2

5

Otmar Hilliges

@OHilliges

2 years

@3DVconf @SattlerTorsten Thanks for inviting me! Really enjoyed giving the talk and the discussions.

0

5

Otmar Hilliges

@OHilliges

11 months

👨‍💻 Demo code: 📄Paper: 📊Dataset: 🎥Video:

Hi4D: 4D Instance Segmentation of Close Human Interaction

Project page: https://yifeiyin04.github.io/Hi4D/

www.youtube.com

0

1

3

Otmar Hilliges

@OHilliges

1 year

@rsasaki0109 Thanks for the highlight. Here are the links to project page & paper: Project: Paper: Video: @ait_eth

Hi4D: 4D Instance Segmentation of Close Human Interaction

We propose Hi4D, a method and dataset for the automatic analysis of physically close human-human interaction under prolonged contact. Robustly disentangling several in-contact subjects is a...

arxiv.org

1

5

Otmar Hilliges

@OHilliges

2 years

With diminished value of social interaction and a #ClimateEmergency going on I cannot justify this additional long-haul flight (already committed to another US trip this year). (5/6).

1

0

5

Otmar Hilliges

@OHilliges

1 year

In FastSNARF, costly MLP evaluations and LBS calculations are replaced by a single tri-linear interpolation step—lightweight and super fast (18x faster). A custom CUDA implementation provides an additional speed-up factor of 8x! 3/6

1

0

5

Otmar Hilliges

@OHilliges

11 months

And we're not stopping here either! Because Tianjian is awesome, he improved the method since acceptance and integrated it with SAM for accurate in-the-wild segmentation. Now InstantAvatar can reconstruct 3D avatars from monocular in-the-wild videos in just minutes! 4/5

1

0

5

Otmar Hilliges

@OHilliges

2 years

We propose a hierarchical RL-based method that decomposes the task into low-level grasping control and high-level motion synthesis. This method can generate novel hand sequences that approach, grasp, and move an object to a desired location, while retaining human-likeness.

1

5

Otmar Hilliges

@OHilliges

11 months

PM - part I:

1

2

Otmar Hilliges

@OHilliges

2 years

Anecdotally many of these cases came from social events. Despite being fully vaxxed I would probably stay away from many of these. (3/6)

1

0

4

Otmar Hilliges

@OHilliges

2 years

We supervise via unlabelled in-the-wild videos with a time-contrastive learning objective. We show that this 1) improves hand reconstruction and yields smoother estimates; 2) significantly improves cross-dataset generalization; 3) similar hand poses are closer in feature space.

1

2

4

Otmar Hilliges

@OHilliges

11 months

PM - part II:

0

3

Otmar Hilliges

@OHilliges

2 years

This is hard since this requires reasoning about the complex articulation of the human hand and the physical interactions with the object (e.g., collisions, friction, gravity). Even ground truth labels from existing grasping datasets do not lead to stable grasps.

1

4

Otmar Hilliges

@OHilliges

11 months

The workshop is organized by: Hyung Jin Chang, @zc_alexfan , @OHilliges , @tkhkaeio , Yoichi Sato, @mu4yang , @angelayao101 . Winners and prizes will be announced and awarded during the #ICCV2023 HANDS workshop. Come join us!

0

1

4

Otmar Hilliges

@OHilliges

11 months

🚗 AssemblyHands Challenge: the AssemblyHands dataset, includes 3rd-person and egocentric images of toy assembly and disassembly, along with 3D hand pose annotations. Participants must estimate 3D hand joints from an egocentric view.

1

4

Otmar Hilliges

@OHilliges

11 months

We propose a hybrid representation that incorporates the advantages of parametric meshes and neural fields. A skinned, animatable mesh is used to store local features at each vertex. A global decoder generates high frequency details from these features. 2/

1

0

3

Otmar Hilliges

@OHilliges

1 year

@ait_eth @mc_buehler @XuChen71058062 and not to forget former lab members Xucong Zhang @xucong_zhang and Wookie Park @swookpark !

2

1

3

Otmar Hilliges

@OHilliges

2 years

We introduce the novel task of dynamic grasp synthesis: given an initial object pose and a static grasp reference, the goal is to move the object to an arbitrary goal position in a human-like, physically plausible way.

1

3

Otmar Hilliges

@OHilliges

11 months

To facilitate future research on expressive avatars, we contribute the X-Humans dataset, containing 233 sequences (20 participants), a total of 35,500 frames. It includes high-quality textured scans of expressive human motions and the corresponding SMPL[-X] registrations. 4/

1

0

3

Otmar Hilliges

@OHilliges

2 years

@dong_zijian @ChenGuo96 Paper: Video:

PINA: Learning a Personalized Implicit Neural Avatar from a Single...

CVPR 2022

www.youtube.com

0

1

2

Otmar Hilliges

@OHilliges

2 years

@NicoChauvin74 @YufengZzzz That should be a matter of days once everyone is back from CVPR; stay tuned

0

2

Otmar Hilliges

@OHilliges

11 months

AM - part II - HOOD & HI4D:

1

0

2

Otmar Hilliges

@OHilliges

11 months

Our method reconstructs individual actors in dynamic interaction with complete geometry & detailed contact info. Thus we attain 3D/2D instance segmentation masks, body model registrations, and vertex-level contact labels. 4/

1

0

2