Autonomous Vision Group @AutoVisionGroup Twitter profile

Last Seen Profiles

@kobronlakeshow

@nna415131850356

@Tsuki_Seiba

@Cougsky

@road_hashas

@jaesoon

@Bahubali_Actor

@booksss_da

@Cuckoldress_Eve

@TannerVolk

@kevinpklau

@PDMbyvXBb0WmOSK

@Krtzyy

@H_10_10_10H

@jelenadjokovic

@goncalooon

@SchoolCaCO3

@StAModLangs

@TiaKofi

@gapjildefender

@RealKeyWestJess

@Kizuna_pro57

@LeslieCaromile

@lattecappucino

@tdogmedia

@hono77372122700

@fields_of_few

@ace_frehley

@MSCCargo

@Coach_Casula

@Aspie_Friendly

@DartmoorPlan

@YasItalian

@TOHBADDI

@lijiaxin97_

@davidfrenchx

Autonomous Vision Group

@AutoVisionGroup

4 months

After 2 years of hard work by the team, we are thrilled to release today! Scholar Inbox is a personal paper recommender which enables you to stay up-to-date with the most relevant progress by delivering personal suggestions directly to your inbox.🧵

13

126

661

Autonomous Vision Group

@AutoVisionGroup

7 months

Why are Tesla @elonmusk and Wayve @alexgkendall @Jamie_Shotton moving towards end-to-end autonomous driving? What is the state-of-the-art in this field? With our friends @francislee2020 we recently wrote an extensive survey paper on this emerging topic:

7

140

634

Autonomous Vision Group

@AutoVisionGroup

1 year

🎅 Today, we have an early Christmas present for you: SDF Studio. Building on the fantastic @nerfstudioteam code, we have integrated various implicit surface reconstruction techniques in one common framework! More algorithms and results coming soon..

6

156

592

Autonomous Vision Group

@AutoVisionGroup

3 years

This is unbelievable: Michael Niemeyer @Mi_Niemeyer won the CVPR 2021 best paper award!! Thanks to Michael and all my fantastic students and postdocs for their extraordinary work! You are just amazing..

45

49

577

Autonomous Vision Group

@AutoVisionGroup

10 months

We have now integrated Neuroangelo into SDF Studio. Works like a charm! Get it from here and - if you are at @CVPR - visit our demo today where you can see SDF Studio in action!

6

99

549

Autonomous Vision Group

@AutoVisionGroup

1 year

I am hiring PhD students and PostDocs! If you like to join a great team to conduct curiosity-driven research on implicit neural 3D representations join us now! Flyer:

11

74

378

Autonomous Vision Group

@AutoVisionGroup

2 years

Just finished recording my last lecture of our self-driving cars course this winter. The entire course including videos, slides and problem sets is now available online!

3

70

380

Autonomous Vision Group

@AutoVisionGroup

5 months

Despite its relevance, it can be hard to get into RL. This motivated us to write "An Invitation to Deep Reinforcement Learning", a tutorial for readers with only basic ML knowledge. Huge kudos to @bern_jaeger for this effort. Help us to spread the word!

4

81

383

Autonomous Vision Group

@AutoVisionGroup

1 year

Did you know that SotA flow, stereo and depth results can be obtained using simple winner-takes all feature correlation without cost-volume post-processing? Impossible? Then try out our new UniMatch model:

2

72

368

Autonomous Vision Group

@AutoVisionGroup

1 year

To level student's background knowledge for our deep learning lecture, I recorded a series of micro tutorials on relevant concepts (linear algebra, differential calculus, probability/information theory). Slides: Videos:

Math for Deep Learning — Andreas Geiger

Lecture: Math for Deep Learning (MaDL) A Short Guided Tour on Linear Algebra and Probability Theory (Prof. Andreas Geiger, University of Tübingen) Course Web...

www.youtube.com

3

67

357

Autonomous Vision Group

@AutoVisionGroup

3 months

Geometric Transform Attention (GTA) is a principled way to encode 3D geometric structure of tokens into vision transformers. This work was done by @takeru_miyato in collaboration with @wellingmax and @bern_jaeger . Project page & code:

2

60

330

Autonomous Vision Group

@AutoVisionGroup

2 years

In RegNeRF we investigate how geometry and appearance can be regularized through rendered patches from unobserved viewpoints. This enables training Mip-NeRF from only 3 images. Great collaboration with the Google team.

2

45

307

Autonomous Vision Group

@AutoVisionGroup

2 years

Little reminder about our self-driving cars lecture with 1000+ slides and >20h video lectures which we made public. Pen and paper as well as coding exercises will follow during the semester!

1

52

300

Autonomous Vision Group

@AutoVisionGroup

2 years

What is the best representation for radiance fields? We consider a feature volume as a 4D tensor and propose to factorize this tensor into multiple compact low-rank components leading to state-of-the-art results in <10 min using pure PyTorch. @eccvconf .

1

50

272

Autonomous Vision Group

@AutoVisionGroup

3 years

We received this year's teaching award for our lecture Computer Vision! All slides, videos and problems are available online. Hope they are useful also to people outside Tübingen!

0

35

271

Autonomous Vision Group

@AutoVisionGroup

7 months

We have an opening for a PhD student or PostDoc to build the next-generation of generative 3D models! This will be a collaboration with @fedassa @Mi_Niemeyer @mjoech from Google Zürich. We are looking forward to you joining our team! Flyer:

6

58

271

Autonomous Vision Group

@AutoVisionGroup

5 months

3D Gaussian Splatting is fantastic, but suffers from severe aliasing when changing the focal length or depth from the one used during training. Mip-Splatting addresses this problem in a principled way and provides alias-free reconstructions and renderings.

2

58

250

Autonomous Vision Group

@AutoVisionGroup

2 years

Depth and normal cues extracted from monocular images are complementary to reconstruction cues. We show that they significantly improve the performance of implicit surface reconstruction methods. New work by Zehao Yu et al. to appear at NeurIPS 2022:

1

51

229

Autonomous Vision Group

@AutoVisionGroup

2 years

One of our most surprising findings this year: Perceptual features in the discriminator dramatically improve GAN convergence and FID scores across SotA models, but it only works when adding deterministic random projections! We still don't know exactly why.

3

52

223

Autonomous Vision Group

@AutoVisionGroup

3 years

KITTI has received the ICCV 2021 Everingham prize! Big thanks to all collaborators and the award committee for this recognition! With Philip Lenz, Christoph Stiller and @RaquelUrtasun .

10

22

207

Autonomous Vision Group

@AutoVisionGroup

9 months

Excited to announce our new work on a unified formula for neural fields (Factor Fields) and a novel dictionary factorization (Dictionary Fields, SIGGRAPH 2023)!

1

42

203

Autonomous Vision Group

@AutoVisionGroup

3 years

Wohoo! Congratulations to Michael Niemeyer @Mi_Niemeyer for his GIRAFFE work being selected as a CVPR'21 best paper candidate. 32 out of ~10k submissions have been nominated, amongst those 4 papers from Tübingen! 🎉🍾🥳

0

12

176

Autonomous Vision Group

@AutoVisionGroup

2 years

The Autonomous Vision Group offers research fellowships for Ukrainian PhDs/PostDocs/researchers at risk in CV/NLP/ML as well as software engineering positions for BSc/MSc students. Please contact us for details and forward this to anyone this might apply to. Thanks.

3

49

171

Autonomous Vision Group

@AutoVisionGroup

5 months

Congratulations to @songyoupeng for a very successful PhD defense - and great cake at the after event party.

2

5

173

Autonomous Vision Group

@AutoVisionGroup

9 months

UniMatch, our unified framework for flow, stereo and depth estimation has been accepted by TPAMI! Congratulations to @haofeixu and team for this fantastic work, demonstrating how far strong features can take us, even with simple winner-takes-all matching.

2

42

168

Autonomous Vision Group

@AutoVisionGroup

9 months

ELLIS PhD program 2024 call for applications: Apply and join one the largest PhD and PostDoc program on machine learning and AI in Europe! Deadline: November 15.

ELLIS PhD Program: Call for applications 2023

The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of...

ellis.eu

2

46

165

Autonomous Vision Group

@AutoVisionGroup

2 years

Can we use explicit representations to model implicit surfaces? In Shape as Points we propose a differentiable Poisson solver which does exactly that. Lightweight. Interpretable. 10x faster than neural implicits (eg, Occupancy Networks).

5

27

163

Autonomous Vision Group

@AutoVisionGroup

2 years

ATISS is a new model for indoor scene synthesis which generates a room based on its floor plan. We consider rooms as unordered sets of objects and train our model to be permutation invariant which is critical when working with sets.

3

15

158

Autonomous Vision Group

@AutoVisionGroup

2 years

We are grateful to receive the Longuet-Higgins Prize at CVPR 2022. Thank you.

0

13

149

Autonomous Vision Group

@AutoVisionGroup

2 years

Excited to announce VoxGRAF w/ @K_S_Schwarz @AxSauer @Mi_Niemeyer : Motivated by INGP, we bring good old voxels back to the game of 3D aware image synthesis! Cool result: Rendering from any view is super fast (5 ms) after generating a feature grid (200 ms).

0

24

143

Autonomous Vision Group

@AutoVisionGroup

11 months

Just arrived in Vancouver for @CVPR . My first conference as a program chair! I'm super excited.

1

3

141

Autonomous Vision Group

@AutoVisionGroup

2 years

Today's GANs suffer from high frequencies artifacts. While most works attribute these to the generator, other works point to the discriminator. We rigorously analyze both the generator and discriminator in toy settings to shed light onto this problem.

2

26

137

Autonomous Vision Group

@AutoVisionGroup

3 years

ICCV is nearing its end. I compiled a little playlist with talks I gave this year, covering datasets, metrics, neural scene representations, human avatars and self-driving. I hope we see each other live again next year!

0

22

139

Autonomous Vision Group

@AutoVisionGroup

2 months

In GraphDreamer we distill editable compositional 3D reconstructions from 2D diffusion models using scene graphs as intermediate representation. To appear at CVPR 2024. Paper & Code:

0

22

132

Autonomous Vision Group

@AutoVisionGroup

4 months

I am extremely excited to announce that we will release the result of 2 years of work on December 20! Stay tuned ..

0

14

131

Autonomous Vision Group

@AutoVisionGroup

11 months

The Scholar Inbox team and ambassadors are ready for @CVPR ! All attendees will receive an email within the next days to create their personal CVPR program.

4

14

128

Autonomous Vision Group

@AutoVisionGroup

2 years

Did you ever want to create a 3D avatar of yourself using only an RGB video from your smartphone? Now you can with ARAH: Animatable Volume Rendering of Articulated Human SDFs. Joint work with Shaofei @SiyuTang3 @K_S_Schwarz to appear at @eccvconf :

2

18

127

Autonomous Vision Group

@AutoVisionGroup

3 months

Do not only follow influencers. Also read what's relevant to you! Yes, you can:

Delip Rao e/σ

@deliprao

3 months

Crazy AF. Paper studies @_akhaliq and @arankomatsuzaki paper tweets and finds those papers get 2-3x higher citation counts than control. They are now influencers 😄 Whether you like it or not, the TikTokification of academia is here!

65

281

2K

2

16

125

Autonomous Vision Group

@AutoVisionGroup

7 months

Congratulations to @Mi_Niemeyer for defending his PhD thesis summa cum laude! Very well done!

3

5

125

Autonomous Vision Group

@AutoVisionGroup

10 months

Back in 2015, when we did our own little NeRF.. we should have given it a better name 😉

International Conference on 3D Vision

@3DVconf

10 months

Best Paper Award at #3DV2015 Towards Probabilistic Volumetric Reconstruction using Ray Potentials Ali Ulusoy @AliOsmanUlusoy , Andreas Geiger @AutoVisionGroup , and Michael Black @Michael_J_Black #TBThursday #3DV2024

1

9

103

1

9

124

Autonomous Vision Group

@AutoVisionGroup

1 year

We made SNARF 150x faster!! Fast-SNARF enables very fast and simultaneous optimization of shape and skinning weights given deformed observations without correspondences. Joint work with @XuChen71058062 @OHilliges @Michael_J_Black . Code available at:

2

19

118

Autonomous Vision Group

@AutoVisionGroup

1 year

We have now integrated BakedSDF's neural SDF meshing into SDF studio! Works like a charm! Full-Resolution Example: SDF Studio:

1

22

118

Autonomous Vision Group

@AutoVisionGroup

1 year

Monocular geometric cues do not only help reconstruction but also open world object detection! Check out our new ICLR'23 paper GOOD: Exploring geometric cues for detecting objects in an open world: Joint work with @hhwpku @isDanZhang

0

25

115

Autonomous Vision Group

@AutoVisionGroup

9 months

New team picture of the Awesome Vision Group! Just returning from our 2023 summer retreat on castle Lichtenstein.

0

9

115

Autonomous Vision Group

@AutoVisionGroup

2 years

The Autonomous Vision Group is looking for a PhD student at the intersection of NLP and CV to help revolutionize scientific discovery in the age of exponential research growth. Please help share with potential candidates!

2

29

112

Autonomous Vision Group

@AutoVisionGroup

3 years

This semester, we are teaching a new computer vision course at the University of Tübingen:

0

13

110

Autonomous Vision Group

@AutoVisionGroup

8 months

Excited to share that just 1.5 years after submission, Carolin's TPAMI paper finally got accepted! This was a big project with many ups and downs. Finally, we were able to show some pretty nice material reconstructions with our self-made hand-held scanner:

5

9

92

Autonomous Vision Group

@AutoVisionGroup

3 years

What can 1000 NeRF models do for you? Render 1000 times faster than a single NeRF! Sounds strange? Read @ChrisJReiser 's blog on KiloNeRF:

0

12

94

Autonomous Vision Group

@AutoVisionGroup

8 months

Since 3 months (silence period) have passed, I am now happy to share the talk I gave in the CVPR'23 workshop on Common Misconceptions in Autonomous Driving: The respective papers appear at ICCV'23 and CoRL'23.

[CVPR'23 WAD] Keynote - Andreas Geiger, Universität Tübingen

Talk given at the CVPR Workshop on Autonomous Driving 2023: https://cvpr2023.wad.vision/.00:00 Introduction03:12 nuPlan04:53 Open-Loop and Closed-Loop05:57 L...

www.youtube.com

0

16

92

Autonomous Vision Group

@AutoVisionGroup

8 months

I am super excited to announce that in 3 weeks at ICCV we will be presenting AG3D, a model that learns to generate novel realistic 3D humans from 2D images alone. It wasn't clear at all if this could work. The more exciting we got about the results:

1

15

91

Autonomous Vision Group

@AutoVisionGroup

4 months

Did you know? has been created by scientists for scientists. As we are using it ourselves, we understand the community's needs. Of course, we also appreciate your feedback! Together, let's give scientists the best tools so they can focus on science!

3

11

89

Autonomous Vision Group

@AutoVisionGroup

4 months

Did you know? doesn't just recommend articles that are trending on social media. also recommends articles that don't get as much attention but are equally relevant to your research interests. Sign up today to look beyond the hype!

3

10

86

Autonomous Vision Group

@AutoVisionGroup

4 months

We at love open access and believe that all research should be freely available! We therefore index all 2.4M arXiv articles, covering physics, math, computer science, quant. biology, finance, statistics, electrical engineering and economics.

2

5

87

Autonomous Vision Group

@AutoVisionGroup

1 year

We are organizing the 1st Workshop on End-to-End Autonomous Driving at @CVPR 2023! Paper submission deadline: February 20, 2023

2

17

85

Autonomous Vision Group

@AutoVisionGroup

4 months

Many of you have asked for a more detailed explanation on how works and its functionality. We have now written a little blog post that explains it:

0

14

83

Autonomous Vision Group

@AutoVisionGroup

7 months

Today, I assumed my 3 year term as head of the department of computer science at @uni_tue . First task completed: Organized our faculty retreat at castle Weitenburg!

2

1

85

Autonomous Vision Group

@AutoVisionGroup

2 years

I am hiring new PhD students via ELLIS: If you are interested in working with us, consider to apply to ELLIS! (Deadline: November 15)

ELLIS PhD Program: Call for applications 2022

The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of...

ellis.eu

1

25

80

Autonomous Vision Group

@AutoVisionGroup

2 years

Shaofei @sfwang0928 turned a 30 second video clip of me into this funny dancing 3D avatar using ARAH. Download ARAH and create your own avatars: 🕺

0

11

80

Autonomous Vision Group

@AutoVisionGroup

4 months

We are looking for a motivated postdoctoral researcher interested in NLP for scientific document analysis! If you know someone interested - let us know. Flyer:

0

35

78

Autonomous Vision Group

@AutoVisionGroup

5 months

Given a monocular video, IntrinsicAvatar learns animatable clothed human avatars with decomposed intrinsic properties including albedo, material, and geometry. It was a great @ELLISforEurope collaboration with @SiyuTang3 , @sfwang0928 and @anticboz !

1

13

74

Autonomous Vision Group

@AutoVisionGroup

3 years

ELLIS is recruiting new PhD students. Come join us! Application deadline: 15.11.2021

1

26

76

Autonomous Vision Group

@AutoVisionGroup

10 months

Congrats to our students @KatrinRenz and @songyoupeng for winning the ICVSS best presentation award!

0

3

73

Autonomous Vision Group

@AutoVisionGroup

1 year

The new semester starts soon, and with it a new edition of our Computer Vision lecture. Looking forward to it!

1

6

70

Autonomous Vision Group

@AutoVisionGroup

3 years

Our Deep Learning lecture at @uni_tue is featured by Analytics India Magazine as one of the top 15 YouTube channels to follow for deep learning enthusiasts!

Top 15 YouTube Channels To Follow For Deep Learning Enthusiasts

We have listed down the top 15 YouTube resources to learn deep learning for free.

analyticsindiamag.com

0

12

69

Autonomous Vision Group

@AutoVisionGroup

11 months

Excited to share that our team won the 2023 nuPlan challenge! We will soon release more details, and present the approach at @CVPR ! 🚗🚙🚕

Kashyap Chitta

@kashyap7x

11 months

🎉 Proud and excited to announce that our team won the 2023 nuPlan Challenge! This is the first large-scale benchmark for real-world vehicle motion planning. Kudos to @DanielDauner who was the primary contributor. Team: @MHallgarten0797 , @AutoVisionGroup , and me.

1

6

71

1

10

69

Autonomous Vision Group

@AutoVisionGroup

5 months

Feeling overwhelmed by the daily arXiv paper dump?

1

69

Autonomous Vision Group

@AutoVisionGroup

3 years

ATISS is @paschalidoud_1 's new work on generating, completing and manipulating indoor scenes at the object level. It's fast and leads to consistent results. Nice collaboration with @FidlerSanja 's team.

AK

@_akhaliq

3 years

ATISS: Autoregressive Transformers for Indoor Scene Synthesis pdf: abs: project page:

1

16

104

0

16

70

Autonomous Vision Group

@AutoVisionGroup

2 years

We are super excited to release our latest generative model StyleGAN-XL which will appear at SIGGRAPH 2022: . StyleGAN-XL achieves SotA results on ImageNet and FFHQ 1K, even outperforming recent diffusion models. Great work by @ax_sauer and @K_S_Schwarz !🧵

2

4

68

Autonomous Vision Group

@AutoVisionGroup

9 months

@ChrisJReiser is presenting MERF at SIGGRAPH today! MERF enables memory-efficient radiance fields for real-time view synthesis of unbounded scenes. Great collaboration with @jon_barron @BenMildenhall @szeliski @PeterHedman3 ! Check Christian's live demos:

1

6

66

Autonomous Vision Group

@AutoVisionGroup

2 years

We finally released all benchmarks for the KITTI-360 dataset and got our TPAMI paper on KITTI-360 accepted! Huge shout out to Yiyi Liao for her hard work on this. Is KITTI-360 relevant to you? Find out in her new blog post:

KITTI-360

With the recently released dataset KITTI-360, we develop a set of novel benchmarks to facilitate research at the intersection of vision, graphics and robotics.

autonomousvision.github.io

0

13

66

Autonomous Vision Group

@AutoVisionGroup

1 year

The Tübingen AI Center is looking for 2 postdoctoral researchers interested in computer vision and machine learning! Flyer: Feel free to forward this flyer to suitable candidates. We are looking forward to working with you on exciting research problems!

1

26

62

Autonomous Vision Group

@AutoVisionGroup

2 years

MetaAvatar is a practical approach to generate realistic animatable 3D human avatars from as little as 8 depth maps (eg. Kinect) in only 2 minutes. Key to this is a meta-learned hypernetwork and a model of pose-dependent deformations in canoncial space.

1

8

63

Autonomous Vision Group

@AutoVisionGroup

4 months

The team wishes you a Merry Christmas! (.. and that you are not getting scooped during the holidays)

2

1

62

Autonomous Vision Group

@AutoVisionGroup

2 years

#NeuesProfilfoto

0

1

62

Autonomous Vision Group

@AutoVisionGroup

1 year

A fast and compact NeRF model for dynamic scenes with disentangled representation.

AK

@_akhaliq

1 year

NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields abs: project page:

3

70

300

0

12

62

Autonomous Vision Group

@AutoVisionGroup

10 months

🚙Excited to release CARLA Garage (a set of SOTA self-driving baselines for CARLA) alongside an #ICCV2023 paper which identifies hidden biases and uncovers the secrets of self-driving on CARLA: . Joint work with @Kait0o0 @kashyap7x .

0

13

60

Autonomous Vision Group

@AutoVisionGroup

5 months

@haofeixu 's MuRF is a new feed-forward NVS model with SotA performance on sparse small and sparse large baseline settings. Key for efficiency and quality: a convolutional radiance decoder in the target frustum. Code:

0

16

59

Autonomous Vision Group

@AutoVisionGroup

5 months

We had a nice (early) pre-Christmas Sushi dinner with the group yesterday. Great to see several new faces!

1

3

58

Autonomous Vision Group

@AutoVisionGroup

3 years

Want to do your ML/CV/NLP/Robotics PhD with two top researchers in Europe? Apply to the ELLIS PhD program, the central entry point for excellent ML research in Europe!

ELLIS

@ELLISforEurope

3 years

ELLIS PhD Program in #machinelearning now accepting applications (deadline: November 15, 2021). Details on the program and the application process here:

7

209

418

0

11

59

Autonomous Vision Group

@AutoVisionGroup

2 years

PlanT (CoRL'22) is a learned planner for self-driving based on object-level representations and a transformer architecture which can explain its decisions by identifying relevant objects. Joint work with @KatrinRenz @kashyap7x @MerceaOtniel @zeynepakata

0

9

55

Autonomous Vision Group

@AutoVisionGroup

11 months

@CVPR AC Workshop in progress! Full day mix of talks, posters, townhalls and debates. Currently debate on foundation models and embodiment running..

4

6

57

Autonomous Vision Group

@AutoVisionGroup

3 years

The preprint about our new KITTI-360 dataset and its benchmarks and challenges is now online! We hope many people will find this dataset useful and that it will push self-driving and research at the intersection of vision, robotics and learning.

KITTI-360: A Novel Dataset and Benchmarks for Urban Scene...

For the last few decades, several major subfields of artificial intelligence including computer vision, graphics, and robotics have progressed largely independently from each other. Recently,...

arxiv.org

1

12

56

Autonomous Vision Group

@AutoVisionGroup

11 months

Had a wonderful group BBQ yesterday!

0

51

Autonomous Vision Group

@AutoVisionGroup

5 months

WildFusion! Our brand new 3D aware generative diffusion model.

Katja Schwarz

@K_S_Schwarz

5 months

Excited to share WildFusion! WildFusion requires *only* unposed, single-view images for training but can generate novel instances from varying viewpoints. Project Page: @seungkim0123 @JunGao33210520 @FidlerSanja @AutoVisionGroup @karsten_kreis

7

36

184

0

3

52

Autonomous Vision Group

@AutoVisionGroup

1 year

We thank VolkswagenStiftung for a Momentum research grant to support our project which aims to accelerate research through AI based research recommendations and analysis. Our first mission is to support @CVPR 2023 with personalized conference programs.

0

7

49

Autonomous Vision Group

@AutoVisionGroup

2 months

🆕Feature alert: now allows researchers to export bibtex information directly to Zotero, Mendeley or any other reference manager!

1

8

50

Autonomous Vision Group

@AutoVisionGroup

4 months

NeLF-Pro represents and reconstructs diverse natural scenes using spatially distributed, learnable light field probes. Nice work by Zinuo You and @AnpeiC that shows how large inhomogeneous scenes can be represented as radiance fields. Project & Code:

0

11

48

Autonomous Vision Group

@AutoVisionGroup

3 years

Our 5 papers at ICCV 2021 at one glance:

ICCV 2021 Papers

www.youtube.com

0

5

47

Autonomous Vision Group

@AutoVisionGroup

3 years

Despoina's @paschalidoud_1 latest results on unsupervised shape abstraction: Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks. Joint work with NVIDIA @FidlerSanja .

Neural Parts: Learning Expressive 3D Shape Abstractions with Invert...

Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods...

www.youtube.com

0

13

48

Autonomous Vision Group

@AutoVisionGroup

10 months

Common Misconceptions in Autonomous Driving. Many people asked for the slides of my talk in the WAD workshop at @CVPR . Here they are:

0

11

45

Autonomous Vision Group

@AutoVisionGroup

2 years

Little reminder about our deep learning lecture with 1000+ slides and >20h video lectures which we made public. Pen and paper as well as coding exercises will follow during the semester!

2

6

46

Autonomous Vision Group

@AutoVisionGroup

3 years

Proud to announce SNARF by @XuChen71058062 - our ICCV'21 work on animating neural implicit shapes with amazing generalization capabilities. This was a great collaboration between ETHZ, MPI-IS and Uni Tübingen!

SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural...

Neural implicit surface representations have emerged as a promising paradigm to capture 3D shapes in a continuous and resolution-independent manner. However,...

www.youtube.com

0

5

45

Autonomous Vision Group

@AutoVisionGroup

2 years

Excited to present KING @ ECCV 22 w/ NiklasH @KatrinRenz @kashyap7x @apratimbh : Using differentiable kinematics, our method generates novel safety-critical driving scenarios which improve the robustness of imitation learning based self-driving agents!

0

14

44

Autonomous Vision Group

@AutoVisionGroup

2 years

Today and yesterday I presented some of our recent work on self-driving, generative modeling and neural rendering & reconstruction at ECCV workshops. If you like to get a quick overview on AVG's latest research, you can watch my talks here:

ECCV 2022 Keynotes

www.youtube.com

0

12

43

Autonomous Vision Group

@AutoVisionGroup

10 months

Mind blowing keynote by Yejin Choi at @CVPR about the future of AI.

0

1

43

Autonomous Vision Group

@AutoVisionGroup

3 months

This year, we again held 3 coding challenges on self driving in OpenAI Gym as part of our self-driving lecture. Congratulations to the winning student teams! 💪

1

43

Autonomous Vision Group

@AutoVisionGroup

2 years

At CVPR 22 we present "gDNA: Towards Generative Detailed Neural Avatars", our first work on synthesizing novel human bodies in clothing from a collection of static scans with realistic wrinkles! Collaboration with ETHZ and MPI-IS.

0

2

42

Autonomous Vision Group

@AutoVisionGroup

1 month

GenAD: A Generalized Predictive Model for Autonomous Driving. Great collaboration with @francislee2020 and team!

Generalized Predictive Model for Autonomous Driving

In this paper, we introduce the first large-scale video prediction model in the autonomous driving discipline. To eliminate the restriction of high-cost data collection and empower the...

arxiv.org

Hongyang Li

@francislee2020

1 month

The Generalised Predictive Model for Autonomy comes onto the stage !! Good attempt to see if massive public data (as pre-training) could help the driving task in context of video prediction. Nice collaboration with @AutoVisionGroup #CVPR2024 @CVPR

1

17

51

2

6

40

Autonomous Vision Group

@AutoVisionGroup

9 months

Flashback to 2017 when we worked on sparsity invariant CNNs for processing irregular sensory data like LIDAR maps.

International Conference on 3D Vision

@3DVconf

9 months

Best Student Paper Award at #3DV2017 Sparsity Invariant CNNs Jonas Uhrig, Nick Schneider, Lukas Schneider, Thomas Brox, Andreas Geiger @AutoVisionGroup #TBThursday #3DV2024

0

5

29

1

2

42

Autonomous Vision Group

@AutoVisionGroup

5 months

We have added several nice, real-time interactive demos to the Mip-Splatting project page that run in your browser, check them out here:

0

7

41