Michael Black
@Michael_J_Black
Followers
73K
Following
10K
Media
535
Statuses
3K
Director, Max Planck Institute for Intelligent Systems (@MPI_IS). Chief Scientist @meshcapade. Building 3D digital humans using vision, graphics, and learning.
Tübingen, Deutschland
Joined April 2010
Code and data are now online for CameraHMR, our state-of-the-art parametric 3D human pose and shape (HPS) estimation method that will appear at hashtag#3DV2025. There are 4 key contributions that make it so accurate and robust:. 1. To get accurate 3D
5
38
213
I get a lot of reviews that say my work is not novel and I bet I'm not alone. It's always frustrating because I see novelty where the reviewer doesn't. Rather than rebut every critique, I've written a blog post to help reviewers think about novelty.
72
882
3K
PhD students, don't worry. Technologies, trends, and even whole fields come and go. A PhD makes you an expert in a field but, more importantly, teaches you how to become an expert. Once you know that you can learn anything, you can adapt to major disruptions in your field.
59
437
3K
I asked #Galactica about some things I know about and I'm troubled. In all cases, it was wrong or biased but sounded right and authoritative. I think it's dangerous. Here are a few of my experiments and my analysis of my concerns. (1/9).
85
762
3K
In the LLM-science discussion, I see a common misconception that science is a thing you do and that writing about it is separate and can be automated. I’ve written over 300 scientific papers and can assure you that science writing can’t be separated from science doing. Why? 1/18.
40
497
2K
The Max Planck Society has pledged to support Ukrainian scientists who have to flee and need a place to work. If you are a computer vision scientist leaving #Ukraine, reach out to me.
8
335
1K
Young scientists regularly ask me for career advice. Academia or industry? Big company or startup? US or Europe? Good scientists in AI disciplines are fortunate to have many choices. But choosing can be stressful. I always give the same advice. 1/10.
21
245
1K
arXiv can result in a time travel situation where you find out your daughter is also your mother. We put a paper on arXiv. Someone else built on it, cited us, and published before us. Fine. Now reviewers want us to explain our novelty beyond the published paper. Now what?.
41
120
1K
Build what you need and use what you build. This is a core philosophy of my research. It shifts the focus away from publishing “papers” to what really matters — impact. This thread unpacks why I think this is a successful approach to science. 1/10 Or see:.
17
268
1K
Failure is the dance partner of success. It can feel insurmountable at times. Here is my story of academic failures -- my anti-CV if you will. I hope people find it useful.
32
216
970
The 5 stages of rebuttal grief. (1) Denial.The reviewers totally misunderstood my paper. The review process is broken. R1 was clearly a student who has never reviewed before. R2 doesn’t know what they are talking about. R3 hates me.
13
163
902
WHAM defines the new state of the art in 3D human pose estimation from video. By a large margin. It’s fast, accurate, and it computes human pose in world coordinates. It’s also the first video-based method to be more accurate than single-image methods. 1/8
15
111
802
I think the rule that you do not need to cite arXiv papers in CVPR/ICCV/ECCV submissions confuses people. If you build on prior work, then you must cite it. If that work appeared in arXiv or was painted on the sidewalk, it doesn't matter.
11
55
766
So I got this nice award (PAMI Distinguished Researcher). PAMI is the name of a journal and the technical committee that helps run our field. But for me it’s more. It’s a home that’s supported and nurtured my career. A scientist doesn’t make a career on their own. 1/3
62
24
777
If you believe that social media can replace peer review, consider my experience. Every paper I've published has been improved by peer review. I can't say the same for comments on Twitter. I may not always agree with reviewers but they spend hours with my paper, not seconds.
35
49
732
It offers authoritative-sounding science that isn't grounded in the scientific method. It produces pseudo-science based on statistical properties of science *writing*. Grammatical science writing is not the same as doing science. But it will be hard to distinguish. (6/9).
10
75
681
Why dangerous? Galactica generates text that's grammatical and feels real. This text will slip into real scientific submissions. It will be realistic but wrong or biased. It will be hard to detect. It will influence how people think. (5/9).
15
80
589
I applaud the ambition of this project but caution everyone about the hype surrounding it. This is not a great accelerator for science or even a helpful tool for science writing. It is potentially distorting and dangerous for science. (9/9).
32
41
564
Summarizing my CVPR reviews: reviewers prefer a poor solution to a new problem over a really good solution to an existing problem. A field needs both. If every paper proposes a new problem, we will never make progress on any of them.
10
52
548
With LLMs for science out there (#Galactica) we need new ethics rules for scientific publication. Existing rules regarding plagiarism, fraud, and authorship need to be rethought for LLMs to safeguard public trust in science. Long thread about trust, peer review, & LLMs. (1/23).
28
124
473
Stepping outside my area of expertise, I’m frustrated that Europeans are not being asked to reduce their energy use. In addition to showing solidarity with #Ukraine, it would enable the EU to impose stronger sanctions against Russia. 1/4.
14
49
458
Now you can try out BITE (#CVPR2023) on @huggingface and create a 3D model of your dog from a single image. Have fun!
7
125
455
HAAR is a generative model of 3D hair. Given a text description, HAAR generates an encoding of the 3D hair strands. These are decoded into an animation-ready hair model. This connects text-driven generative models with standard graphics that can be used today, eg in Unreal. 1/5
12
69
458
Who should be the last/senior author on a paper? How do you decide? What does being last entail? I get these questions a lot and it’s confusing because the last author is often a senior person, running a group & raising money. Do those things determine last authorship? No. (1/7).
16
66
437
This could usher in an era of deep scientific fakes. Alldieck and Pumarola will get citations to papers they didn't write. These papers will then be cited by others in real papers. What a mess this will be. (7/9).
9
42
418
I find myself repeating the same advice to students again & again. So I finetuned Mistral.APR.01 on the last 4 years of my Slack history. Now it's answering questions for me. I can go biking for a week and nobody notices. I think my students may actually be getting better advice.
15
23
430
Writing your Ph.D. thesis? I have one request. Read every single word from beginning to end before giving it to your advisor. Every word. Straight through. You will immediately find things that are out of order, don't hang together, and don't form a coherent story.
13
19
428
I’m honored to share the 2020 Longuet-Higgins prize with @DeqingSun and Stefan Roth. It is given at #CVPR2020 for work from #CVPR 2010 that has withstood the test of time. I’ve written a blog post about the secrets behind “The Secrets of Optical Flow”:
19
76
429
Understanding human behavior requires understanding 3D human contact with the world. To study this, we introduce a dataset (RICH) and a method (BSTRO) that infers 3D contact on the body from a single image. #CVPR2022 (1/8)
7
81
396
There's a problem with 3D human pose & shape (HPS) estimation methods. You either get good 3D accuracy or good alignment with the image, but not both. Why? The current top methods use the wrong camera model. TokenHMR at #CVPR2024 analyzes the issue and presents a solution. (1/8)
9
65
403
Train your avatars to interact with 3D scenes. We use adversarial imitation learning and reinforcement learning to train physically-simulated characters that perform scene interaction tasks in a natural and life-like manner. Today at #SIGGRAPH2023.
5
60
390
When failure's not an option, success isn't possible. You can quote me on that.
20
51
390
Anyone who has taught knows the following is true. You think you understand something until you go to teach it. Explaining something to others reveals gaps in your understanding that you didn’t know you had. Well, writing a scientific paper is a form of teaching. 2/18.
4
26
375
This is why I find AR more exciting than VR. It’s the ability to extend human perception beyond the visible spectrum that will literally let us understand the world in new ways.
Finally, you can literally "grab" your #wifi signal and find your #network dead spots in #mixedreality. Special thanks to the @BadVR_Inc team for putting together such a handy app. Link below 👇. #technology #QuestPro
7
48
379
The #CVPR2024 deadline is approaching and it's time to “Dance with the one who brung ya” - this is the phrase I use before a deadline when your results fall short of your dream (as they often do). It means to accept what you have and make the most of it. 1/4.
4
43
380
Today marks my 10th anniversary of living on Germany. It was my honor to co-found the @MPI_IS together with @bschoelkopf and to build the @PerceivingSys department together with amazing students, postdocs, and staff, past and present (. My deepest thanks.
11
5
378
Nature: 10 reasons to move to Germany as a researcher. All true! They miss some other reasons: 1. vacation and a belief that it is important to take it (even PhD students). 2. Higher education and science are valued by society. Being a Prof. Dr. is cool.
9
36
373
A critical skill for scientists is to know what you know and to know what you don't know. And then admit what you don't know to yourself and others. LLMs like #ChatGPT are hugely impressive but to make them useful for science, the ability to say "I don't know" is necessary.
24
39
362
If we are going to have fake scientific papers, we might has well have fake reviews of fake papers. And then we can also have fake letters of reference for fake academics who get promoted to tenure at fake universities. I can then retire as there is nothing left for me to do.
19
29
348
What’s the key enabling technology of the #metaverse?. It’s not #VR headsets, #AR glasses, or #avatars with legs. It’s computer vision (CV) and @Meta clearly understands this. We focus on headsets & avatars because they're tangible, visible, artifacts in a way that CV isn’t. 🧵.
7
38
355
Summary: science thinking, writing, and doing are inseparable. Focus on story. Write early. Write a shitty first draft. And do yourself a favor: write it yourself. I promise that writing about your science will improve your science. 18/18.
13
35
339
It is not the "smartest" people who succeed in science. It takes intrinsic motivation, perseverance, the drive to stay active and hands on, a strong support network of mentors, and the curiosity to keep learning. Nice summary in Nature:
1
53
344
I hear a lot about how "speed" is critical to scientific progress. We are obsessed with speed these days. I think accuracy and correctness are what are really important. In my experience correctness and speed of often inversely correlated. So don't be fooled by speed demons.
11
33
338
Given the outside surface of the human body, can we peer inside and infer the bones? Many methods predict a “skeleton” that is not realistic. With OSSO (#CVPR2022), for the first time, we learn to predict a detailed skeleton from external observations. (1/7)
5
64
336
Upgrade your expressive 3D human avatars from #SMPL-X to #SUPR, our latest and greatest body model. SUPR is trained from 1.2M 3D scans, is more expressive, and includes feet with articulation and compression. Code by @NeelayShah8, video by @AYiannakidis.
13
54
338
New @CVPR2020. VIBE: Video Inference for Human Body Pose and Shape Estimation. SOTA 3D human pose and shape from video. @mkocab_ & @athn_nik at @PerceivingSys .Code etc.: Video:
1
80
329
As an advisor, there is nothing better than seeing your students and post docs succeed, grow, and become part of the community. This group is so impressive. I love how they support each other and I love their intellectual curiosity. I’m only sad for the ones who couldn’t come.
14
9
336
This was my first CVPR and nobody told us we were getting an award. Anandan and I skipped the banquet where the prize was awarded. David Kriegman accepted it on our behalf and for the rest of the conference people were congratulating him. Lesson: never skip the awards session!.
CVPR 1991 Best Paper Award. Robust Dynamic Motion Estimation over Time. @Michael_J_Black and P. Anandan. #TBThursday
4
21
325
AI-generated reviews of scientific papers are increasing, vacuous, and need to be stopped quickly. They reduce author trust in the review process. Proposal: someone who is judged to have submitted such a review is banned from submitting to the same conference/journal for 2 years.
36
31
315
I always assumed language is harder than vision since it evolved later. Even simple species have vision that allows survival. Thus, I thought we’d solve the “vision problem” before higher-level reasoning. That language is helping us solve the vision problem has been a surprise.
32
29
323
I'm sure the authors are aware of the dangers. Every generation comes with the fine print "WARNING: Outputs may be unreliable! Language Models are prone to hallucinate text." But Pandora's box is open and we won't be able to stuff the text back in. (8/9).
4
27
296
I was honored to accept the Koenderink Prize at @eccvconf 2022 on behalf of my coauthors Dan Butler, Jonas Wulff, and Garrett Stanley. The prize recognizes the Sintel optical flow dataset paper for standing the test of time. Behind the scenes blog post:
17
20
313
This is an interesting, timely, and important paper. The takeaway is that "recent self-supervised models such as DINOv2 learn representations that encode depth and surface normals, with StableDiffusion being a close second". This contrasts with vision-language models like CLIP,.
Google announces Probing the 3D Awareness of Visual Foundation Models. Recent advances in large-scale pretraining have yielded visual foundation models with strong capabilities. Not only can recent models generalize to arbitrary images for their training task, their
8
40
312
Computer vision for animals is a growing sub-field that will have a big impact. We have organized a CVPR workshop that brings together amazing keynote speakers. All we need now is you! Please submit your work even if it is preliminary.
6
90
300
Poster practice session for #cvpr2022 was a ton of fun. My job was to pretend to be all sorts of poster visitors. They are ready for New Orleans!
6
4
310
The best work I've done has felt like play. I get almost a giddy excitement from new ideas. There is nothing better than working with good people who share your excitement. If you can find a place where work feels like play, you're very lucky. 4/10.
2
29
297
I repeat: Easily produced science text that's wrong does not advance science, improve science productivity, or make science more accessible. I like research on LLMs but the blind belief in their goodness does a disservice to them and science. Here is an example from #ChatGPT 1/5
7
29
293
I don't usually respond to obvious trolling because it just gives more attention to the troller. But if you're curious about what I actually wrote about #Galactica in Nov 2022, you can read it for yourself here: I concluded with: "I applaud the ambition.
Will @Grady_Booch, @GaryMarcus, @Michael_J_Black, and others ever rescind their prophecies of LLM-powered doom for the scientific community. It seems that the release of ChatGPT, a mere few weeks after Galactica, and the groundswell of public interest in it made them hold their.
12
15
290
.@thiemoall publishes in the area (excellent work BTW) so it's on the right track but it has made up this reference. Based on these few tests, I think #Galactica is 1) an interesting research project, 2) not useful for doing science (stick with wikipedia), 3) dangerous. (4/9).
4
25
279
While most existing methods that estimate 3D human pose and shape (HPS) do so in camera coordinates, many applications require 3D humans in global coordinates. At #CVPR2023, we introduce TRACE, which addresses this using a novel 5D representation. 1/6
4
62
292
Repeat after me: "Reviewer 2 is not an idiot. It's my fault for not writing things more clearly.".
32
25
286
I think about the field of 3D human pose, shape, and motion estimation as having three phases. 1: Optimization. 2: Regression. 3: Reasoning. With #PoseGPT, we are just entering phase 3. I summarize the coming paradigm shift in this blog post:
2
53
268
Today is my last day at #Amazon. I joined over 4 years ago as a Distinguished Amazon Scholar (20% time) through the acquisition of Body Labs. It has been an amazing experience, I’ve learned a lot, and will always be grateful for the opportunity. (1/8).
3
3
281
These are exciting times. There's a sense that AI will change everything, including how science is done. Implicit in this excitement is the hope that everything will change for the better. Let’s look at that. First, we need to define “better.”.
11
58
266
Thanks to everyone at #CVPR2024 who's come up and thanked me for my blog and social media posts. Knowing they've been useful to you encourages me to keep sharing. One thing I love about CVPR is meeting new people so don't be shy -- come say hi. And, yes, we can take a selfie :).
5
5
275
Only in #SanFrancisco does this ad make sense on a bullock at the train station. A key rule of advertising is to know your customer. Nailed it. I'm thinking, "yes, indeed, I do want to save $20M on my next H100 bill".
12
26
268
I’m a competitive person. I like to win. So I find myself as an unlikely advocate of failure on X. I find myself writing about it a lot. When I write about failure, however, I’m really writing about risk. And to embrace risk is to embrace the possibility of both success and.
8
31
270
GenAI systems create realistic images or basic 3D shapes from text. We take a different approach and use AI to control classical 3D graphics models, turning AI into a computer-graphics artist. We demonstrate this approach by generating novel 3D trees and animals. 1/8
6
45
267
The German Chancellor, Angela Merkel, visited @MPI_IS today to hear about @Cyber_Valley - virtually of course. Here she is getting a tour of the @PerceivingSys capture hall. It was fun, she asked great questions, and the team was awesome!
3
31
258
@jbhuang0604 All good points but let me add one more. Use the work yourself. Build on it. In this way you teach others how it is useful. If it isn’t foundational for you, why would it be for others?.
2
13
262
Not only does our paper achieve state-of the-art-results, we include a proof of something completely irrelevant.
2
12
256
The name has changed but it remains the world's first 3D human foundation model. ChatPose (formerly PoseGPT) has a new name at the request of the #CVPR2024 reviewers. Same great work from @meshcapade and @PerceivingSys. Final #CVPR2024 version on arXiv:
4
57
261
Should you do research in a AI startup? Does it burn someone else's money and your equity? Or is it the key to success? If you do it, how do you manage it? Drawing on experiences at Xerox PARC, Amazon, Body Labs, & @meshcapade, I try to shed some light:
5
38
255
BEV (#CVPR2022) computes all the 3D people in an image in one shot, placing them all appropriately in depth. The key novelty is an imaginary 2D “Bird’s-Eye-View” (BEV) representation that reasons about the body centers in depth. (1/8)
2
52
245
If you missed my talk on 3D Human Foundation Agents at Stanford yesterday and want to check it out, here's the recording:
6
47
249
Is it my imagination or are the ads longer than the talks at #ECCV2020? It changes the character of the scientific meeting. I love an expo, but let the science be ad-free. Let's call this a worthwhile experiment that failed and let's not do it again.
9
16
247
I wanted to build a 4D body scanner at Brown and wrote an NSF proposal with a colleague to fund it. We got high scores for everything but the final analysis was that they didn't think anyone needed 4D body scans. That gave me the kick to move to MPI where I could pursue my dream.
Our highlight in 2013 was the @PerceivingSys new state-of-the-art 4D body scanner. @Michael_J_Black & his team set up the first version that year. Since then, many prominent people have stood in it. Only recently, we captured the motion of the Vice-President of the EU Commission
3
9
249
I entered "Estimating realistic 3D human avatars in clothing from a single image or video". In this case, it made up a fictitious paper and associated GitHub repo. The author is a real person (@AlbertPumarola) but the reference is bogus. (2/9)
3
32
236
Motion: All CVF conferences will have a dataset review process for papers promising a dataset. Acceptance will be conditional on the dataset being ready and reviewed by the camera-ready deadline. Papers that do not comply will be rejected. Comments please:
15
54
251
Is synthetic data “all you need” to train 3D human pose and shape (HPS) regressors? Is the field making progress? What algorithmic decisions matter? To address these questions, we present BEDLAM (#CVPR2023 highlight paper), a synthetic dataset of 3D humans. 1/11
2
49
238
Entrepreneurs and academics have more in common than many people realize. 1. Both imagine some future that doesn't yet exist and seems impossible to others. 2. The really important new ideas are uncomfortable to the establishment and will face resistance. Disruption scares.
12
40
240
A founder needs to be articulate and be able to describe their business succinctly 🤪
18
13
237
@OHilliges My wife has had #MECFS since the 1990's. One doctor told her "You're tired? We're all tired. Go home and have babies." On the other hand, the head of rheumatology at Stanford told her "Don't let anyone tell you that you're not sick." More research is desperately needed.
6
13
214
Avatars are central to the success of the #metaverse and #metacommerce. We need different #avatars for different purposes: accurate #3D digital doubles for shopping, realistic looking for #telepresence, stylized for fun, all with faces & hands. @meshcapade makes this easy. (1/8)
9
48
224
The writing reveals what you don’t know. Years ago, Michal Irani gave me good advice. She said you can write the introduction to your paper long before the science is done and that this helps structure your thinking. 4/18.
2
8
220
I'm rather proud of this timeline and excited to see how the field of 3D human pose and shape (HPS) estimation develops.
Recovering 3D Human Mesh from Monocular Images: A Survey
5
30
224
BITE (#CVPR2023) reconstructs 3D dog shape and pose from one image, even with challenging poses like sitting and lying. Such poses result in occlusion and deformation. Key idea: leverage ground contact to better estimate pose and shape. 1/6
6
30
219
Realistic 3D human animation is hard. Goal: automate it using only speech. Given a speech signal as input, TalkSHOW (#CVPR2023) generates realistic, coherent, and diverse holistic 3D motions, that is, the body motion together with facial expressions and hand gestures. (1/8)
2
34
216
Given the interest in my thread about managing research in academia, I thought I would share my thoughts about managing research in industry. What I learned as a manager at Xerox PARC, is that managing research takes guts — this is probably true about managing anything creative.
2
41
216
The value of synthetic data in Nature. I’m a believer.
7
46
215
Yesterday was my birthday and the folks at @meshcapade made me this wonderful movie. I love fonts and this is the best font ever! I'm going to call it "Avatar". It's #SMPL to make me happy.
11
7
215
Congratulations @YaoFeng1995 for successfully defending your PhD thesis on "Learning Digital Humans from Vision and Language"! DECA, PIXIE & SCARF advanced the capture of faces, full bodies, & bodies in clothing, while ChatPose connects LLMs with 3D humans for the first time.
12
10
217
We've seen rapid progress on generating human motion from text descriptions. But to be really useful, animators need timeline control. With our new work, one can control when multiple actions occur and these actions can even overlap. Great #Nvidia internship by @MathisPetrovich.
Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation. paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from
6
39
204
Social media, influencers, and science publication: I wrote up my thoughts in this blog post. My take on this may surprise people who know my public opposition to promoting papers that are under review.
16
34
202
There is no globally-optimal life. There is no sequence of choices in life that will produce the "perfect life" or "perfect career". This is hard to accept but, once you accept it, it's very freeing. 2/10.
1
19
202
Thirty years ago I dreamt of computers that could see us. Understand us. Move like us. Look like us. And ultimately be like us. So I started building. And I haven’t stopped. @meshcapade is that dream come true. We’re building the future. And the future is now.
10
25
206