Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Most multi-view reconstruction models need full supervision. We show they can self-improve without any ground truth labels. Introducing SelfEvo: Self-Improving 4D Perception via Self-Distillation. Up to +36.5% in video depth, +20.1% in camera estimation, zero annotation.

Qianqian Wang

4,581 subscribers

24,560 просмотров • 2 месяцев назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,523 просмотров • 9 месяцев назад

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 просмотров • 1 год назад

Modality Forcing - turns FLUX.2.klein into 3D-aware models. - joint RGB-D, I2D, and D2I synthesis in one model - pixel-space depth tokenization - preserves T2I quality via self-distillation

Modality Forcing - turns FLUX.2.klein into 3D-aware models. - joint RGB-D, I2D, and D2I synthesis in one model - pixel-space depth tokenization - preserves T2I quality via self-distillation

Wildminder

13,049 просмотров • 16 дней назад

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation Contributions: • We propose a novel approach to inject SfM priors into diffusion-based depth estimation, enabling highly accurate and multi-view consistent depth predictions for each viewpoint. • Based on the proposed depth estimator, we design a new multi-view 3D geometry reconstruction framework and process some synthetic datasets to facilitate training. • We evaluate our method on diverse real-world scene data, including objects, indoor environments, streetscapes, and aerial scenes, demonstrating the superior performance and generalization capability of our approach.

Multi-view Reconstruction via SfM-guided Monocular Depth Estimation Contributions: • We propose a novel approach to inject SfM priors into diffusion-based depth estimation, enabling highly accurate and multi-view consistent depth predictions for each viewpoint. • Based on the proposed depth estimator, we design a new multi-view 3D geometry reconstruction framework and process some synthetic datasets to facilitate training. • We evaluate our method on diverse real-world scene data, including objects, indoor environments, streetscapes, and aerial scenes, demonstrating the superior performance and generalization capability of our approach.

MrNeRF

25,651 просмотров • 1 год назад

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

Stability AI

197,288 просмотров • 1 год назад

Can robots self-improve by collecting data autonomously🤖? Introducing SOAR: a system for large-scale autonomous data collection 🚀 and autonomous improvement📈of a multi-task language-conditioned policy in diverse scenes without human interventions .

Can robots self-improve by collecting data autonomously🤖? Introducing SOAR: a system for large-scale autonomous data collection 🚀 and autonomous improvement📈of a multi-task language-conditioned policy in diverse scenes without human interventions .

Paul Zhou

47,667 просмотров • 1 год назад

Google presents CAT4D Create Anything in 4D with Multi-View Video Diffusion Models

Google presents CAT4D Create Anything in 4D with Multi-View Video Diffusion Models

AK

61,949 просмотров • 1 год назад

Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds! No expensive optimization needed, yet delivers SOTA results for: ✅ Camera Pose Estimation ✅ Multi-view Depth Estimation ✅ Dense Point Cloud Reconstruction ✅ Point Tracking Project Page: Code & Weights:

Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds! No expensive optimization needed, yet delivers SOTA results for: ✅ Camera Pose Estimation ✅ Multi-view Depth Estimation ✅ Dense Point Cloud Reconstruction ✅ Point Tracking Project Page: Code & Weights:

Jianyuan

203,120 просмотров • 1 год назад

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

Hila Chefer

67,648 просмотров • 3 месяцев назад

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.

Joy Hsu

14,843 просмотров • 2 лет назад

Emad Mostaque says Elon Musk is about to use 100,000 GPUs — more than anyone else to train video models A video model learns the world's physics, then scales to generate any 3D asset "video models are world models" they can simulate entire environments to improve things like self-driving cars

Emad Mostaque says Elon Musk is about to use 100,000 GPUs — more than anyone else to train video models A video model learns the world's physics, then scales to generate any 3D asset "video models are world models" they can simulate entire environments to improve things like self-driving cars

Haider.

28,506 просмотров • 11 месяцев назад

I had an awesome time interviewing idan shenfeld and Jonas Hübotter from MIT and ETH Zurich about self-distillation. this very promising post-training paradigm where the model acts as its own teacher by conditioning on environment feedback or demonstrations. we cover the SDPO algo for reinforcement learning with rich feedback and SDFT for continual learning without forgetting along with many applications. we dig into how it works, why it's simpler and faster than GRPO, and where this is already showing up in production systems. table of content: 0:00 - what is self distillation 2:50 - idan (MIT) and jonas (ETH Zurich) introduction and motivation 18:40 - different perspective of on-policy self-distillation (presentation) 36:00 - metacognition and specificity in self-distillation 37:24 - very long hard task and self-distillation 42:00 - continual learning with self-distillation (presentation) 1:16:50 - what is next in this research direction? 1:20:00 - is there any experience with subjective feedbacks? 1:22:50 - quality vs number of feedbacks? 1:26:40 - what setting would self-distillation struggle vs GRPO? the slides were super crisp really cool of them to share! enjoy my guys 🌹

I had an awesome time interviewing idan shenfeld and Jonas Hübotter from MIT and ETH Zurich about self-distillation. this very promising post-training paradigm where the model acts as its own teacher by conditioning on environment feedback or demonstrations. we cover the SDPO algo for reinforcement learning with rich feedback and SDFT for continual learning without forgetting along with many applications. we dig into how it works, why it's simpler and faster than GRPO, and where this is already showing up in production systems. table of content: 0:00 - what is self distillation 2:50 - idan (MIT) and jonas (ETH Zurich) introduction and motivation 18:40 - different perspective of on-policy self-distillation (presentation) 36:00 - metacognition and specificity in self-distillation 37:24 - very long hard task and self-distillation 42:00 - continual learning with self-distillation (presentation) 1:16:50 - what is next in this research direction? 1:20:00 - is there any experience with subjective feedbacks? 1:22:50 - quality vs number of feedbacks? 1:26:40 - what setting would self-distillation struggle vs GRPO? the slides were super crisp really cool of them to share! enjoy my guys 🌹

Yacine Mahdid

12,988 просмотров • 2 месяцев назад

🚨WATCH: Attorney and Self Defense expert Andrew Branca Show explains why officers were legally justified in the Alex Pretti Shooting. "If there's a gunshot-like noise and the cops just heard "gun, gun, gun," and Alex Pretti's hand comes into view from his waistband with a black object in it, that's going to be a reasonable perception of an eminent deadly force threat." "And that's the justification the officers need to shoot him. They don't need to be correct, by the way, in that perception. No one's required to make perfect decisions in self-defense. We're just required to make reasonable decisions in self-defense." Click the link below to watch the full interview

🚨WATCH: Attorney and Self Defense expert Andrew Branca Show explains why officers were legally justified in the Alex Pretti Shooting. "If there's a gunshot-like noise and the cops just heard "gun, gun, gun," and Alex Pretti's hand comes into view from his waistband with a black object in it, that's going to be a reasonable perception of an eminent deadly force threat." "And that's the justification the officers need to shoot him. They don't need to be correct, by the way, in that perception. No one's required to make perfect decisions in self-defense. We're just required to make reasonable decisions in self-defense." Click the link below to watch the full interview

Brandon Tatum

17,171 просмотров • 5 месяцев назад

Superintelligence will be built on Self Improvement. Today Hexo Labs, we’re excited to release ‘SIA’ - an open-source Self-Improving AI, to achieve any goal through recursive self improvement. While trying to solve a problem, SIA doesn't just improve it's abilities by updating it's harness, it updates it's own weights as well.

Superintelligence will be built on Self Improvement. Today Hexo Labs, we’re excited to release ‘SIA’ - an open-source Self-Improving AI, to achieve any goal through recursive self improvement. While trying to solve a problem, SIA doesn't just improve it's abilities by updating it's harness, it updates it's own weights as well.

Kunal Bhatia

522,527 просмотров • 1 месяц назад

Introducing hands free Tesla Full Self-Driving (Supervised) 12.4.3 Here it is driving from Golden Gate Park to Fort Point with zero interventions. Watch in 4K:

Introducing hands free Tesla Full Self-Driving (Supervised) 12.4.3 Here it is driving from Golden Gate Park to Fort Point with zero interventions. Watch in 4K:

Whole Mars Catalog

6,941,071 просмотров • 2 лет назад

Elon: Unsupervised Full Self-Driving is Coming Globally "We have a full pipeline of major improvements to Full Self-Driving that we believe will lead to unsupervised full self-driving being available anywhere in the world where it is legal.” @ElonMusk

Elon: Unsupervised Full Self-Driving is Coming Globally "We have a full pipeline of major improvements to Full Self-Driving that we believe will lead to unsupervised full self-driving being available anywhere in the world where it is legal.” @ElonMusk

Mario Nawfal

170,717 просмотров • 2 месяцев назад

Biopic of JrNTR becoming a self made star in TFI without any background

Biopic of JrNTR becoming a self made star in TFI without any background

Venki🏏🦁Megaforce

87,151 просмотров • 11 месяцев назад

Do I have any perfectionist, self critical, self sabatoging overthinkers in the chat!? Well then how about you join me in a little Self Compassion, how about we challenge ourselves to talk a little kinder to our good hearts:)?

Do I have any perfectionist, self critical, self sabatoging overthinkers in the chat!? Well then how about you join me in a little Self Compassion, how about we challenge ourselves to talk a little kinder to our good hearts:)?

Brett Eldredge

16,096 просмотров • 1 год назад

Can LLMs Self-Verify? Much better than you'd expect. LLMs are increasingly used as parallel reasoners, sampling many solutions at once. Choosing the right answer is the real bottleneck. We show that pairwise self-verification is a powerful primitive. Introducing V1, a framework that unifies generation and self-verification: 💡 Pairwise self-verification beats pointwise scoring, improving test-time scaling 💡 V1-Infer: Efficient tournament-style ranking that improves self-verification 💡 V1-PairRL: RL training where generation and verification co-evolve for developing better self-verifiers 🧵👇

Can LLMs Self-Verify? Much better than you'd expect. LLMs are increasingly used as parallel reasoners, sampling many solutions at once. Choosing the right answer is the real bottleneck. We show that pairwise self-verification is a powerful primitive. Introducing V1, a framework that unifies generation and self-verification: 💡 Pairwise self-verification beats pointwise scoring, improving test-time scaling 💡 V1-Infer: Efficient tournament-style ranking that improves self-verification 💡 V1-PairRL: RL training where generation and verification co-evolve for developing better self-verifiers 🧵👇

Harman Singh (in NYC for summer)

105,116 просмотров • 3 месяцев назад