Eric Brachmann @eric_brachmann Twitter profile

Pinned Tweet

Eric Brachmann

10 days

📢A new learning-based approach to SfM: #ACEZero No img-to-img matching, optimises image-to-scene correspondences directly. Needs no pose priors. Works on unordered image sets. Efficiently handles thousands of images. Paper: Page:

12

82

437

Last Seen Profiles

@AP_Slush24

@actressstark

@k_myon_RPS13

@myIesjones

@King_soul1st

@SiTuvieseDinero

@znamodanedamo

@jarvisb70

@uniris

@XiuVotingsGuide

@McGarthy

@VersaPulley

@PrithviAdmirers

@KoenraadVan

@WCAboyslacrosse

@MannadiyarTeam

@mfwaimavelikara

@TeamImpu

@prolificdesign5

@drunkccn

@clozelybo

@STAParents

@TheCrimsonPete

@StreamOnMax

@michaelrubin

@NAZ_Elite

@Najam_Zaman_

@hidsayah

@yakultxz

@asifkhalils

@GolotapMr

@_Pisukev

@MindTheGum

@irmag1nation

@bc_lhs_baseball

@AdultReh

Eric Brachmann

@eric_brachmann

23 days

✨ Presenting MicKey ( #CVPR2024 , Oral) ✨ We regress and match 3D camera coordinates rather then 2D key points, all in metric space. Gives you a scaled relative pose between two RGB images. Paper: Page:

8

64

446

Eric Brachmann

@eric_brachmann

11 months

A #CVPR2023 Highlight✨: ♥️♠️ACE: Accelerated Coordinate Encoding♣️♦️ We learn implicit, neural maps in minutes that let us relocalize with SOTA accuracy. 📜: 💻: 📽️: work by @NianticLabs Research

7

108

424

Eric Brachmann

@eric_brachmann

1 year

Good luck, everyone! #CVPR2023

4

20

263

Eric Brachmann

@eric_brachmann

5 years

We release the first code package for NG-RANSAC: Estimating epipolar geometry from sparse correspondences. Implemented in @PyTorch and including various pre-trained models: #ICCV2019 #ICCV19 #ICCV #DeepLearning #ComputerVision #MachineLearning

4

74

250

Eric Brachmann

@eric_brachmann

6 years

We've published @pytorch code of Differentiable RANSAC for a toy problem: fitting lines. A CNN learns to predict points (middle) to which we robustly fit lines, trained end2end with DSAC. Right: A CNN which learns to predict line parameters directly. Code:

1

61

196

Eric Brachmann

@eric_brachmann

3 years

Read papers to write good papers. Review papers to write great papers. Read rebuttals to write good rebuttals. Discuss rebuttals to write great rebuttals. Great papers and great rebuttals are no guarantee to get accepted. Iterations are normal.

2

15

176

Eric Brachmann

@eric_brachmann

3 years

Does the "ground truth" treat you fairly? Watch this shocking #ICCV21video 🤯🤯🤯 You will not believe what a 10-year-old baseline looks like today! #ICCV2021 w/ @martinhu @Carsten_Rother @SattlerTorsten

9

23

157

Eric Brachmann

@eric_brachmann

2 years

Today, we launch Map-Free Visual Relocalisation. A twist on the usual relocalisation formula. A new dataset. A new benchmark. Check out our video! #MapFreeReloc to be presented at #ECCV2022

4

26

146

Eric Brachmann

@eric_brachmann

4 years

Major update and code release for our #relocalization pipeline, DSAC* (Updated) paper: Code: Use RGB or RGB-D, train with an SfM model or a 3D scan. Train from images and poses alone and DSAC* discovers coarse geometry by itself:

3

20

124

Eric Brachmann

@eric_brachmann

22 days

We dedicate our oral presentation at #CVPR2024 in Seattle to R2, who - in a great moment of integrity and reason - raised their initial "weak reject" rating to "strong reject" after rebuttal. We hope they enjoy every minute of our 15 minute talk.

Eric Brachmann

@eric_brachmann

23 days

✨ Presenting MicKey ( #CVPR2024 , Oral) ✨ We regress and match 3D camera coordinates rather then 2D key points, all in metric space. Gives you a scaled relative pose between two RGB images. Paper: Page:

8

64

446

7

13

124

Eric Brachmann

@eric_brachmann

3 years

RGB image in, set of 3D primitives out. A #CVPR2021 paper with @florian_kluger , H. Ackermann, M. Yang and B. Rosenhahn! #ComputerVision abs: code: We take RANSAC out of its comfort zone into scene understanding territory. 👇

2

19

123

Eric Brachmann

@eric_brachmann

3 years

#ICCV2021

0

7

121

Eric Brachmann

@eric_brachmann

7 months

With the #CVPR2023 content being public now, so are the recordings of the talks I gave. Firstly, I gave a talk at the #IMC2023 workshop: "Pose Estimation Beyond Feature Matching" I recommend watching the whole session of this awesome workshop! 1/2

3

25

118

Eric Brachmann

@eric_brachmann

1 year

Calm down everyone, it's just a rotation...

1

5

117

Eric Brachmann

@eric_brachmann

1 year

I really like the Twitter format for presenting papers. So I thought I replicate that for my personal website (neglected for years...) It's a simple static HTML, feel free to use as template.

4

22

112

Eric Brachmann

@eric_brachmann

1 year

Due to requests at #ECCV2022 and to make our #MapFreeReloc dataset useful for more tasks, we make the SfM reconstructions of our train set publicly available. 🔥460 SfM models of outdoor scenes all around the world 🔥 Want to train 460 NeRFs? Go ahead.

6

20

113

Eric Brachmann

@eric_brachmann

4 years

Career update. I have come to chew bubble gum and do kick ass research. And I'm all out of bubble gum. @NianticLabs #80smoviesreferences #augmentedreality #

13

3

107

Eric Brachmann

@eric_brachmann

3 years

All talks of our #ICCV2021 tutorial on visual localisation are available on YouTube. In my talk about learning-based localisation, I discuss a challenge, a promise and a compromise. Watch it here: Links to all the amazing talks in 🧵👇

4

24

107

Eric Brachmann

@eric_brachmann

4 years

Third and last code package for NG-RANSAC ( #ICCV2019 ) is online: NG-DSAC++ for camera re-localization, a re-implementation of DSAC++ in @PyTorch , extended with neural guidance. Code: Paper: w/ @Carsten_Rother @LabHeidelberg

1

27

105

Eric Brachmann

@eric_brachmann

17 days

🔥Map-relative Pose Regression🔥( #CVPR2024 highlight) For years absolute pose regression did not work. There was some success by massively synthesising scene-specific data. We train scene-agnostic APR and it works. Paper: Page:

5

13

106

Eric Brachmann

@eric_brachmann

3 years

Did you know there is a German word for working late into the night towards a deadline? Verschlimmbessern. #CVPR2021

3

5

102

Eric Brachmann

@eric_brachmann

2 years

We are hiring! Want to work with me and an amazing team at @NianticEng on re-localisation at a global scale? Bring cutting-edge research into the hands of millions of users? Consider applying for our Mapping and Localisation MLE role:

0

16

102

Eric Brachmann

@eric_brachmann

11 months

Niantic research has a strong presence at #CVPR2023 with 5 papers (one highlight) and various contributions throughout workshops and tutorials. Diffusion, NeRF, relocalisation, object pose, feature matching, depth and occlusions. Here is where you can catch us:

1

14

100

Eric Brachmann

@eric_brachmann

4 years

2 papers accepted to #cvpr2020 🥳 Reinforced Feature Points: Use classic REINFORCE to optimize feature detection and description for the task you care about CONSAC: fit multiple parametric models by learned sequential search (w/ @florian_kluger ) More info soon! #ComputerVision

7

98

Eric Brachmann

@eric_brachmann

6 years

Efficiency in the deep learning era :) #CVPR2018

1

18

90

Eric Brachmann

@eric_brachmann

3 years

PhD student and looking for an #internship ? Sink your teeth into juicy #MachineLearning and #ComputerVision problems right at the frontier of #AugmentedReality at @NianticLabs ! Spread the word! ❤️❤️❤️

0

31

88

Eric Brachmann

@eric_brachmann

3 years

. @SattlerTorsten talking about "Old School" methods at the #ICCV2021 tutorial on visual localization. "Old" but not outdated! Join us here: I will talk about the "New School" later.

0

14

90

Eric Brachmann

@eric_brachmann

22 days

When you try to solve difficult image pairs, it's important that you do not overshoot and start to hallucinate connections between unrelated images. The #MapFreeReloc benchmark checks for that. The inlier count of MicKey is pretty good in separating solvable and unsolvable cases.

2

7

90

Eric Brachmann

@eric_brachmann

2 months

Dust3r takes over from RoMa as the leading method in #MapFreeReloc !

Jerome Revaud

@JeromeRevaud

2 months

done, DUSt3R now first of the leaderboard!

3

4

58

2

11

85

Eric Brachmann

@eric_brachmann

4 years

Some motivation if you didn't make it into #CVPR : - our first object coordinates paper: rejected from CVPR14, barely made it into ECCV14 (>250 citations) - follow up: rejected from ICCV15, made it into CVPR16 (~200 citations) - ESAC: rejected from CVPR19, made it into ICCV19

3

13

85

Eric Brachmann

@eric_brachmann

1 year

To #CVPR2023 reviewers: Remember there are humans on the other end. Be strict in the matter but respectful in tone. Consider even being friendly in tone. Someone worked hard on this, and is proud. Don't bend but sweeten the pill.

2

8

81

Eric Brachmann

@eric_brachmann

9 months

With the #ACErelocalizer , we reduced mapping times from 15 hours to 5 minutes. You can imagine that further speed improvements are exponentially harder. Yet, we managed to squeeze out another 15% speed-up. Let me walk you through the steps: 1. Upgrade to @pytorch 2.x Fin.

Eric Brachmann

@eric_brachmann

11 months

A #CVPR2023 Highlight✨: ♥️♠️ACE: Accelerated Coordinate Encoding♣️♦️ We learn implicit, neural maps in minutes that let us relocalize with SOTA accuracy. 📜: 💻: 📽️: work by @NianticLabs Research

7

108

424

5

9

80

Eric Brachmann

@eric_brachmann

5 years

New retro wave of #ComputerVision : NG-RANSAC brings you the greatest hits of the 80s: RANSAC, multi-layer perceptrons, (classic) reinforcement learning. Lens flare for visualization of "cool", only. The paper: #ICCV2019 #ICCV19 #ICCV #DeepLearning

2

19

79

Eric Brachmann

@eric_brachmann

3 years

Automatic generation of ground truth is great but caution is advised. Upcoming for #ICCV2021 : For vis. relocalisation, we show that depending on how you generate GT, the ranking of relocalisers flips upside down: @SattlerTorsten @martinhu @Carsten_Rother

4

15

77

Eric Brachmann

@eric_brachmann

1 year

Submitting relocalisation via pose regression to #ICCV2023 ? Rejected from #CVPR2023 ? Consider the #MapFreeReloc benchmark. No need to beat DSAC*, hLoc, AS... they do not apply. This benchmark was created just for you 🫵 Also if you work on: - features - depth - uncertainty 🧵

3

14

76

Eric Brachmann

@eric_brachmann

2 years

We uploaded alternative "ground truth" and full SfM models for the #relocalisation datasets 7Scenes and 12Scenes. Working on reloc towards #ECCV2022 and having trouble beating SOTA? The "ground truth" might play a role. #ICCV2021 #betterlatethannever

1

22

72

Eric Brachmann

@eric_brachmann

8 months

Stumbled across this #ICCV2023 paper extending #MapFreeReloc to panoramic indoor views. Makes a lot of sense: A panorama serves as a one-shot map with wide coverage. Calibrating Panoramic Depth Estimation for Practical Localization and Mapping, Kim et al

1

20

70

Eric Brachmann

@eric_brachmann

2 years

The moment has finally come. I tried to get the best education possible to prepare for this. Worked hard. Let's see whether it all payed off. My son learned the word "why".

4

1

69

Eric Brachmann

@eric_brachmann

22 days

Personally, I find these results all the more remarkable considering that MicKey does not use any cross attention. Key points and descriptors are predicted per image, without considering the other view. Just vanilla matching and RANSAC after that.

Eric Brachmann

@eric_brachmann

23 days

Beyond providing metric estimates, MicKey can also deal with extreme view point changes, up to opposing shots. Here are a few examples of MicKey correspondences.

1

0

18

3

10

69

Eric Brachmann

@eric_brachmann

4 years

Reinforced Feature Points, my first paper as last author, will be presented as an oral at #CVPR2020 🥳🥳🥳 Congrats to @AritraBhowmik6 ! arXiv:

1

15

68

Eric Brachmann

@eric_brachmann

2 years

#LightshipVPS in action. Please note the alignment of the chain with the anchor top 🙀 @LightshipAR @NianticEng #VPS #AR #AugmentedReality

4

10

67

Eric Brachmann

@eric_brachmann

11 months

Learning-based visual relocalisation has made quite some progress over the years. I'm giving an overview in our #CVPR2023 tutorial on: 📢"Large-Scale Visual Localisation" Mark June 19th in your calendar. Check out the full schedule of amazing talks:

3

16

66

Eric Brachmann

@eric_brachmann

3 years

Strange. My Twitter feed somehow suppresses all the tweets of PhD students from small labs that complain about the #CVPR2022 social media motion. I see, however, plenty tweets by 1k+ follower accounts complaining that the former group will be at a disadvantage now 🙃

7

4

65

Eric Brachmann

@eric_brachmann

5 years

My slides for learning-based visual localization of our #iccv2019 tutorial are online:

1

13

62

Eric Brachmann

@eric_brachmann

4 years

Bring me the horizon! I finally managed to prepare the code of NG-DSAC ( #ICCV2019 ) for horizon line estimation. Code: Paper: #deeplearning #machinelearning #computervision

1

14

63

Eric Brachmann

@eric_brachmann

11 months

What's #MapFreeReloc ? A learned model induces a scale-metric space, conditioned on a single reference frame. We localise new queries in that space. I will talk about "Pose Estimation Beyond Feature Matching" on Monday morning at #CVPR2023 at the Image Matching Workshop #IMC2023

1

12

58

Eric Brachmann

@eric_brachmann

5 years

RANSAC vs. USAC vs. NG-RANSAC for essential matrix estimation from SIFT correspondences. Long (and slower) version:

1

10

56

Eric Brachmann

@eric_brachmann

14 days

Dear #ECCV2024 reviewer, "see weaknesses" is not a good "justification of rating". Every paper has weaknesses. The AC needs to understand why you think the weaknesses outweigh the strengths (or vice versa). Best,

2

4

53

Eric Brachmann

@eric_brachmann

2 years

Our call for research interns @NianticEng for 2022 is live! Interested in pushing the frontiers of AR? So are we. Work with us on a wide range of topics in the spectrum of #ComputerVision and #MachineLearning ! Interested? More info and application forms:

3

14

50

Eric Brachmann

@eric_brachmann

4 years

You would assume that since 2012 #DeepLearning was applied to everything and their mother. But, as far as we know, CONSAC is the first learned multi-model robust estimator. By @florian_kluger #CVPR2020 arXiv: code:

2

18

52

Eric Brachmann

@eric_brachmann

5 years

Today, Wednesday morning, at #ICCV2019 , I will present NG-RANSAC at poster stand 143 (far end of the expo hall). I will try to explain the method on a simple toy problem, such that even I could understand it :) Come by, say hello! #ICCV #ICCV19 #DeepLearning #MachineLearning

2

9

52

Eric Brachmann

@eric_brachmann

5 years

Two papers accepted to @ICCV19 ! Neural-Guided RANSAC (NG-RANSAC): A neural network guiding RANSAC data point selection, and Expert Sample Consensus (ESAC): An ensemble of scene coordinate experts for scalable camera re-localization. #ICCV2019 #ComputerVision #DeepLearning

2

8

51

Eric Brachmann

@eric_brachmann

2 years

Who said re-localisation in changing conditions is a problem?

4

1

50

Eric Brachmann

@eric_brachmann

2 years

I keep reading in papers that RANSAC is so excruciatingly slow that getting rid of it is a contribution. Watch DSAC* estimating poses from thousands of correspondences in 30ms per frame, including network execution and RANSAC. 👇 Brrr.

3

51

Eric Brachmann

@eric_brachmann

4 years

Only 6650 actual submissions to #CVPR2020 . End of the world prevented. (3350+ people were just curious what the current submission ID might be?)

Kosta Derpanis

@CSProfKGD

4 years

#CVPR2020 paper ids passed 10,000!

6

73

270

1

17

50

Eric Brachmann

@eric_brachmann

3 years

Hopefully, someday I will review a paper that starts with: "X is not a fundamental problem in computer vision. But we looked into it anyway."

3

0

49

Eric Brachmann

@eric_brachmann

4 years

You know these annoying 16bit PNGs, eg depth maps, that your default image viewer probably does not show correctly? Did you know that #ImageJ can open them? Did you also know that #ImageJ has been ported to JavaScript and runs in your browser!? 😲

2

3

49

Eric Brachmann

@eric_brachmann

6 years

Extending on my earlier post about research trends at #CVPR2018 , I wrote a little python script that plots topic popularity (measured by key word matches against paper titles) over time. It's a simple Jupyter notebook, so you can play around yourself:

1

25

48

Eric Brachmann

@eric_brachmann

3 months

@eccvconf Oh, this is just cruel. Posting this and then it's still that 14 page, 1 column "aesthetic".

3

0

49

Eric Brachmann

@eric_brachmann

11 months

Thanks @ducha_aiki for sharing our work faster than we could get it to arXiv. Its available there as well, now. 📜 TL;DR? Upload the gist of it into your brain via YouTube: ▶️ w/ @axelbarrosotw , @viprad , Gabe, and @dantkz

Dmytro Mishkin 🇺🇦

@ducha_aiki

11 months

Two-view Geometry Scoring Without Correspondences Axel Barroso-Laguna, @eric_brachmann Victor Adrian Prisacariu Gabriel Brostow @dantkz tl;dr: in title + nice analysis of the metrics for the epipolar geometry.I almost want to write a blogpost-review :)

2

20

85

2

14

46

Eric Brachmann

@eric_brachmann

3 months

@taiyasaki The ECCV template is extra punishment for getting rejected from CVPR.

1

3

47

Eric Brachmann

@eric_brachmann

11 months

📢📢 Announcing the 8th workshop on Recovering 6D Object Pose ( #R6D ) at #ICCV2023 📢📢 CFP: We invite paper submissions of unpublished works covering object pose estimation and related topics. Deadline: July 24 #BOP challenge 2023 also in the works!

1

15

47

Eric Brachmann

@eric_brachmann

5 months

How to explain the difficulties of hyper-parameter tuning to non-experts.

2

1

45

Eric Brachmann

@eric_brachmann

3 years

I really like that I'm not able to rate "borderline" in the final #ICCV2021 assessment. I'm split regarding several submissions, now I have to think twice as I have to lean in some direction. An unexpectedly enjoyable inner fight.

0

2

45

Eric Brachmann

@eric_brachmann

2 years

Turning regression into classification problems is one of the most unappealing workarounds we currently often resort to, I find.

6

3

43

Eric Brachmann

@eric_brachmann

2 years

6/6 #CVPR2022 reviews done. Strong stack this one: worst score is borderline - never had this before. Innovative ideas and above-average writing. I'm impressed.

0

44

Eric Brachmann

@eric_brachmann

4 years

The slides for my talk at the R6D workshop at #iccv2019 are available at the workshop website: A summary of our work on differentiating PnP, differentiable RANSAC, differentiable correspondence selection and differentiable expert selection. #DeepLearning

1

10

43

Eric Brachmann

@eric_brachmann

2 years

Noone: "The ECCV template is beautiful and should never be changed." #ECCV2022

2

0

43

Eric Brachmann

@eric_brachmann

6 years

Finally, there is an extensive benchmark for 6D object pose estimation, presented at #ECCV2018 . No learned method in top 3. Best learned method uses Random Forests instead of CNNs. Want to defend the honor of deep learning? It's a running competition ;)

2

26

42

Eric Brachmann

@eric_brachmann

3 years

Something I wanted to talk about so often to so many people was finally accepted at #ICCV2021

1

41

Eric Brachmann

@eric_brachmann

5 years

#iccv #iccv19 #iccv2019 #nerdculture

1

9

42

Eric Brachmann

@eric_brachmann

11 months

📢 Benchmark for 6D Object Pose Estimation 📢 #BOP challenge 23 opened! Results to be presented at the #R6D workshop at #ICCV2023 . The challenge has always pushed the field forward. This year: ❓unseen objects❓. Can you onboard a new object in 5mins?

2

14

40

Eric Brachmann

@eric_brachmann

3 years

A small thread on 3D rotations: Both log-quaternions (log-q) and axis-angles (aa) represent rotations with 3 parameters. But they are not the same, related by a factor of 2. The length of aa gives you the rotation angle, the length of log-q gives you half that angle.

2

8

38

Eric Brachmann

@eric_brachmann

3 years

Struggling to understanding SE(3)? You are certainly not alone. The thread below and all its replies collect a wonderful list of resources.

Andrew Davison

@AjdDavison

3 years

This summer I've been working to finally understand Lie Theory, the basis for proper estimation on over-parameterised manifolds like SE(3). There are some great tutorials for the roboticist out there; I especially like Micro Lie Theory by Solà et al.

13

109

639

0

8

40

Eric Brachmann

@eric_brachmann

5 years

On Wednesday I will be giving a talk at @naverlabseurope on visual localization. I will talk about differentiable RANSAC and new stuff, including learning to guide RANSAC and scalable re-localization. If you are in Grenoble, come by!

1

7

39

Eric Brachmann

@eric_brachmann

2 years

Got a 6D pose paper accepted to #CVPR2022 or #ECCV2022 ? Great! You convinced the reviewers, now convince everyone else. The #BOP challenge accepts your submission until 14th Oct. @ma_sundermeyer @tomhodan @eccvconf Your paper was rejected? 🧵👇

1

6

38

Eric Brachmann

@eric_brachmann

4 years

To add to my list of motivating failures: I had 2 submissions lined up for #ECCV2020 . One stopped a few weeks ago, one stopped a few hours before deadline. So that happens, too! At the same time, this is my contribution to #slowscience . You are welcome 😜

Eric Brachmann

@eric_brachmann

4 years

Some motivation if you didn't make it into #CVPR : - our first object coordinates paper: rejected from CVPR14, barely made it into ECCV14 (>250 citations) - follow up: rejected from ICCV15, made it into CVPR16 (~200 citations) - ESAC: rejected from CVPR19, made it into ICCV19

3

13

85

0

39

Eric Brachmann

@eric_brachmann

2 years

Sounds like something awesome is about to happen in the #AugmentedReality landscape. 😃 Visual reloc here and there, surely soonish everywhere.

Niantic Launches City-scale Visual Positioning System for Multi-user AR

Niantic today launched its Lightship Visual Positioning System at its first developer summit. The system aims to form an underlying 3D map of the world so that AR devices can share the same frame of...

www.roadtovr.com

0

3

37

Eric Brachmann

@eric_brachmann

6 years

All slides of our #ECCV2018 tutorial on visual localization are now online, including the parts about learned methods:

Visual Localization - ECCV 2018 Tutorial

Course Information When: Saturday, September 8th, 2018 Where: N1070ZG, Technische Universität München Arcisstraße 21, 80333 Munich (https://goo.gl/maps/tZENRFMpcwD2) Time: Morning Schedule 9:00 -...

sites.google.com

1

22

36

Eric Brachmann

@eric_brachmann

3 years

One of our drafts was rejected from #ICCV2021 . While Im not happy with the reasoning of the ACs, I do appreciate the transparency. It is clear the draft was flagged by the AC as needing discussion, that the disc. had room, and what the disc. was. @ICCV_2021 setting new standards.

1

0

36

Eric Brachmann

@eric_brachmann

4 years

Hot off the arXiv press: Results of the #BOPchallenge of this years #ECCV20 in handy paper format: What's the best 6D object pose estimator in town? Do we still need depth for high accuracy? Thanks @tomhodan and @ma_sundermeyer for putting it together.

0

12

35

Eric Brachmann

@eric_brachmann

1 year

📢The #BOPchallenge2022 report is here! How did object pose estimation evolve since #BOP 2020? - Avg precision 69.8% (2020) -> 83.7% (2022) 📈 - Training on synthetic data costs you merely 1% 🤖 - top RGB method of 2022 beats top RGB-D method of 2020 🤼

1

6

35

Eric Brachmann

@eric_brachmann

16 days

In my visual relocalization tutorial talks, I always had an up-to-date slide measuring the progress of APR methods compared to classical approaches (dotted line). Took us less than 10 years 💪

Eric Brachmann

@eric_brachmann

17 days

🔥Map-relative Pose Regression🔥( #CVPR2024 highlight) For years absolute pose regression did not work. There was some success by massively synthesising scene-specific data. We train scene-agnostic APR and it works. Paper: Page:

5

13

106

2

6

35

Eric Brachmann

@eric_brachmann

4 years

If you are interested in visual camera re-localization: We improved DSAC++ a bit, and called it DSAC*. I still have to prepare the code but you can have a peak at the tech report below. Trains faster, tests faster, less memory, more accuracy. Also, RGB-D if you want.

1

9

35

Eric Brachmann

@eric_brachmann

4 years

Quick glimpse at our #CVPR2020 oral on end-to-end learning of sparse feature detection, including discrete matching and RANSAC-based model fitting. But don't waste your time on the 1min version, you will anyway want to learn more... The full sweet 5mins:

Reinforced Feature Points

Our paper titled "Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task" has been accepted in CVPR 2020 as an oral pr...

www.youtube.com

Aritra Bhowmik

@AritraBhowmik6

4 years

Here is our 1min teaser video on reinforcing feature points, selected as an oral in #CVPR2020 , narrated by me! w/ @eric_brachmann @Carsten_Rother Prof. Gumhold. Paper : Full video : #ComputerVision #DeepLearning #CVPR #oral #ML

0

3

13

3

17

34

Eric Brachmann

@eric_brachmann

10 months

Looks like we have a new top entry for #MapFreeReloc with huge improvements over SuperGlue and LoFTR. @Parskatt wasted no time after my #IMC2023 talk at #CVPR2023 . Judging from the entry title, it's this paper:

2

9

34

Eric Brachmann

@eric_brachmann

1 month

The 2023 BOP challenge report is out, measuring progress in 6DoF instance pose estimation: Accuracy is excellent if objects are known in advance. For unseen objects, still pretty good but slow! Middle: best method for known objects, right: unseen obj.

1

3

34

Eric Brachmann

@eric_brachmann

2 years

Join us at #3DV2021 , oral session 3 (9am/10pm GMT) where we are about to present Visual Camera Re-Localization using Graph Neural Networks and Relative Pose Supervision Stellar work by @0ozgur0 during an internship at @NianticEng .

1

7

33

Eric Brachmann

@eric_brachmann

4 years

We should rethink the distinction of hand-crafted vs. learning-based. Learning-based methods are hand-crafted (architecture, flow of information, domain knowledge), and hand-crafted methods have free parameters. Often the distinction is: Who optimizes the parameters, you or ADAM?

3

2

33

Eric Brachmann

@eric_brachmann

1 year

Ommm. I will not become Schmidhuber. Ommm. I will not become Schmidhuber. Ommm. I will not become Schmidhuber. Ommm. I will not become Schmidhuber. Ommm. I will not become Schmidhuber. Ommm. I will not become Schmidhuber. ...

Eric Brachmann

@eric_brachmann

1 year

@ducha_aiki @ixtiyoruz312 @yash_patel2307 @majti89 If the paper claims that there is no differentiable RANSAC yet in the first paragraph while citing a paper that has differentiable RANSAC in the name, I certainly have questions that require more than 7 lines.

1

16

3

0

31

Eric Brachmann

@eric_brachmann

1 year

Occam's razor of engineering: If two systems perform comparably, prefer the simpler one. The fewer components, fewer things can break on unseen data.

2

0

32

Eric Brachmann

@eric_brachmann

5 years

Today, Thursday afternoon, at #ICCV2019 I'll present our 2nd poster. ESAC, a variant of (differentiable) RANSAC, allows you to train an ensemble of expert networks. I'll explain it using lines and circles but it can also solve useful problems - like re-localization. Poster #153

0

6

30

Eric Brachmann

@eric_brachmann

5 years

Doing my CVPR reviews, I realize how desperately we need a unified evaluation framework for 6D object pose estimation from RGB images. Several great papers have been written on the topic in the last few years, but all of them evaluate slightly differently.

3

1

30

Eric Brachmann

@eric_brachmann

6 months

Did you know there is a German word for finishing your #CVPR2024 paper just in time? Not too early, not too late? Punktlandung.

2

1

30

Eric Brachmann

@eric_brachmann

4 years

The abstract: Convince a potential reviewer, who has zero time, zero attention span, and might see his previous work diminished by your claims, that your research has some worth. In 10 lines. No pressure. #CVPR2020

2

29

Eric Brachmann

@eric_brachmann

4 years

A new iteration of the #R6D workshop is in the making! What object pose estimation #magic have you been cooking up? How did the community progress on this task? Tell us with a paper submission! And get your GPUs warmed up, a new BOP #challenge will be organized as well. #ECCV2020

Tomáš Hodaň

@tomhodan

4 years

We invite paper submissions to the ECCV'20 workshop on recovering 6D object pose! Deadline: July 10.

0

11

32

1

6

29

Eric Brachmann

@eric_brachmann

2 years

How do you relax while working? I copy results into excel sheets by hand.

6

0

28

Eric Brachmann

@eric_brachmann

5 years

Back in the office after the deadline, archiving the data... #iccv19

1

2

27

Eric Brachmann

@eric_brachmann

5 years

Just wasted an hour trying to create a mesh from a noisy point cloud... Clearly, 2019 is not ready for this. Any hints highly appreciated. I was using MeshLab but found it quite useless for this task. On the other hand, I was just pressing random buttons like a monkey.

5

2

27