正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

AK

473,974 subscribers

28,746 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

3 条评论

AK 的头像

AK1 年前

discuss:

Acellus Academy 的头像

Acellus Academy1 年前

Study Online with Acellus Gold, Designed to Accelerate Learning & Motivate K-12 Student Achievement.

Anda 的头像

Anda1 年前

"Hmm, this makes me wonder if blockchain's immutability could learn from counterfactual motion concepts - like digital footprints that never were but inform the path forward!" 🐾🎋

相关视频

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

Introducing “FlowMap”, the first self-supervised, differentiable structure-from-motion method that is competitive with conventional SfM like Colmap! IMO this solves a major missing piece for internet-scale training of 3D Deep Learning methods. 1/n

Vincent Sitzmann

128,543 次观看 • 2 年前

Pixie Fast and Generalizable Supervised Learning of 3D Physics from Pixels

Pixie Fast and Generalizable Supervised Learning of 3D Physics from Pixels

AK

21,434 次观看 • 9 个月前

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy) 🌐 Project: (1/4)

Supervised learning has held 3D Vision back for too long. Meet RayZer — a self-supervised 3D model trained with zero 3D labels: ❌ No supervision of camera & geometry ✅ Just RGB images And the wild part? RayZer outperforms supervised methods (as 3D labels from COLMAP is noisy) 🌐 Project: (1/4)

Hanwen Jiang

69,460 次观看 • 1 年前

Echoes of Another World Made with #Ray2 Camera Motion Concepts #aivideo #conceptart #worldbuilding

Echoes of Another World Made with #Ray2 Camera Motion Concepts #aivideo #conceptart #worldbuilding

Luma AI

32,247 次观看 • 1 年前

Testing Full Self Driving Supervised in Australia

Testing Full Self Driving Supervised in Australia

Ryan's Model Y

46,484 次观看 • 9 个月前

BTS: Echoes of Another World Made with #Ray2 Camera Motion Concepts #aivideo #conceptart #worldbuilding

BTS: Echoes of Another World Made with #Ray2 Camera Motion Concepts #aivideo #conceptart #worldbuilding

Luma

232,508 次观看 • 1 年前

Scenes of Japan – Still Views Made with #Ray2 Camera Motion Concepts #aivideo #japan #visualstorytelling

Scenes of Japan – Still Views Made with #Ray2 Camera Motion Concepts #aivideo #japan #visualstorytelling

Luma AI

12,101 次观看 • 1 年前

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: • We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.

MrNeRF

53,292 次观看 • 1 年前

I flipped through 300 pages of deep learning math puzzles by hand ✍️ This is the proof copy of the "Deep Learning Math Workbook" I made to help you learn and practice 12 foundational math concepts below👇

I flipped through 300 pages of deep learning math puzzles by hand ✍️ This is the proof copy of the "Deep Learning Math Workbook" I made to help you learn and practice 12 foundational math concepts below👇

Tom Yeh

2,378,310 次观看 • 1 年前

Tesla Full Self-Driving (Supervised) 13.2 exits Universal Studios

Tesla Full Self-Driving (Supervised) 13.2 exits Universal Studios

Whole Mars Catalog

117,562 次观看 • 1 年前

Self-supervised representation learning looks a bit like RL. What if we literally use RL as a SSL method for visual representations? Turns out that it works quite well. In new work by Dibya Ghosh, we show how this can be done:

Self-supervised representation learning looks a bit like RL. What if we literally use RL as a SSL method for visual representations? Turns out that it works quite well. In new work by Dibya Ghosh, we show how this can be done:

Sergey Levine

48,688 次观看 • 11 个月前

Tesla Full Self-Driving (Supervised) 13.2.8 is the best self-driving system I've ever seen

Tesla Full Self-Driving (Supervised) 13.2.8 is the best self-driving system I've ever seen

Whole Mars Catalog

82,414 次观看 • 1 年前

My one year of self learning animation TT

My one year of self learning animation TT

Lunacy(COMMS PAUSED)💜💔🐢⏳

20,820 次观看 • 5 个月前

In 2019, Elon said HW3 was enough for Full Self-Driving. Seven years later, it needs to be Supervised by a human due to safety concerns. Tesla calls it Full Self-Driving Supervised, because they know it will make dangerous maneuvers at any given moment.

In 2019, Elon said HW3 was enough for Full Self-Driving. Seven years later, it needs to be Supervised by a human due to safety concerns. Tesla calls it Full Self-Driving Supervised, because they know it will make dangerous maneuvers at any given moment.

Miss Jilianne

14,891 次观看 • 2 个月前

Free Machine Learning with Python Course from IBM Topic covered: - Supervised Learning - Unsupervised Learning - Dimensionality Reduction & Collaborative Filtering 100% FREE Course link 🧵👇

Free Machine Learning with Python Course from IBM Topic covered: - Supervised Learning - Unsupervised Learning - Dimensionality Reduction & Collaborative Filtering 100% FREE Course link 🧵👇

Afiz ⚡️

59,876 次观看 • 3 年前

Eric Jang weighs in on RL vs. supervised learning for humanoid robot manipulation tasks.

Eric Jang weighs in on RL vs. supervised learning for humanoid robot manipulation tasks.

The Humanoid Hub

10,656 次观看 • 10 个月前

We've released 10+ Linear Algebra concepts for Machine Learning! Here's one of the visualization how PCA identifies direction of maximum variance.

We've released 10+ Linear Algebra concepts for Machine Learning! Here's one of the visualization how PCA identifies direction of maximum variance.

TensorTonic

48,303 次观看 • 5 个月前