Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

we mapped tents in Rafah by applying machine learning to high resolution satellite imagery from Planet. we also show damaged buildings from analysis done by corey scher and Jamon Van Den Hoek. 🛰️ read here 🎁: a small thread with some model specifics 🧵

Krishna Karra

1,028 subscribers

82,476 Aufrufe • vor 2 Jahren •via X (Twitter)

Bildung Nachrichten & Politik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

🚀 Free High Quality Satellite Imagery With Playback Today, we're introducing beautiful high quality satellite imagery from the GOES weather satellites. Free for all users: • Access to all 16 bands (L1b products) • Coverage across CONUS, both Mesoscale sectors and Full Disk • Playback with up to 15 frames • Real-time updates • Inspect the data directly on the map Plus subscribers unlock more: • Imagery displayed on a 3D globe (Globe Projection) • Split View to compare bands side-by-side • Playback with up to 50 frames • Smoothing options: see the raw data or a polished look • RenderStream for faster loading when in low cell service areas Tropical season is now here - stay one step ahead Available on: iOS: Android: Browser: And to Plus subscribers using our Windows/Mac App

🚀 Free High Quality Satellite Imagery With Playback Today, we're introducing beautiful high quality satellite imagery from the GOES weather satellites. Free for all users: • Access to all 16 bands (L1b products) • Coverage across CONUS, both Mesoscale sectors and Full Disk • Playback with up to 15 frames • Real-time updates • Inspect the data directly on the map Plus subscribers unlock more: • Imagery displayed on a 3D globe (Globe Projection) • Split View to compare bands side-by-side • Playback with up to 50 frames • Smoothing options: see the raw data or a polished look • RenderStream for faster loading when in low cell service areas Tropical season is now here - stay one step ahead Available on: iOS: Android: Browser: And to Plus subscribers using our Windows/Mac App

WeatherWise.app

31,289 Aufrufe • vor 1 Jahr

Excited to share a few presentations, demos, and workshop talks from our group and collaborators at #ICRA2026! We will present recent work on real-to-sim-to-real robot policy evaluation, model-based planning with learned dynamics, and multi-modal manipulation. We will also have a joint live demo between SceniX and Analog Devices, Inc. on real-to-sim-to-real cable manipulation at the ICRA exhibition. This is a small teaser of what we have been building, with more to come soon! If you are at ICRA, please stop by the sessions or the demo booth. Happy to chat about robot learning, simulation, world models, and sim-to-real!

Excited to share a few presentations, demos, and workshop talks from our group and collaborators at #ICRA2026! We will present recent work on real-to-sim-to-real robot policy evaluation, model-based planning with learned dynamics, and multi-modal manipulation. We will also have a joint live demo between SceniX and Analog Devices, Inc. on real-to-sim-to-real cable manipulation at the ICRA exhibition. This is a small teaser of what we have been building, with more to come soon! If you are at ICRA, please stop by the sessions or the demo booth. Happy to chat about robot learning, simulation, world models, and sim-to-real!

Yunzhu Li

11,344 Aufrufe • vor 4 Monaten

Are we done with object detection? What about tiny objects beyond 200 meters? 🔎 Telescope 🔭 addresses long-range perception by explicitly tackling extreme scale imbalance ⚖️ in images. It hinges on a learnable hyperbolic foveation transform from a low-resolution image, magnifying distant regions 🔍 while compressing nearby ones - effectively normalizing object scales with minimal computational overhead. Objects are detected in the transformed (Riemannian) space using a novel bounding box parameterization and are then mapped back to the original image. Project:

Are we done with object detection? What about tiny objects beyond 200 meters? 🔎 Telescope 🔭 addresses long-range perception by explicitly tackling extreme scale imbalance ⚖️ in images. It hinges on a learnable hyperbolic foveation transform from a low-resolution image, magnifying distant regions 🔍 while compressing nearby ones - effectively normalizing object scales with minimal computational overhead. Objects are detected in the transformed (Riemannian) space using a novel bounding box parameterization and are then mapped back to the original image. Project:

Felix Heide

188,738 Aufrufe • vor 5 Monaten

NEW: Detailed assessment of the Israeli strike on Taleghan 2, a site "used by the Iranian regime to advance nuclear weapons capabilities," according to the IDF. We detail the damage done to the newly constructed, bunkered facility, and nearby structures. Below is a composite image created by transparently overlaying the post-strike satellite photograph taken by Vantor on 11 March 2026 onto earlier pre-strike imagery. The overlays are designed to demonstrate the high precision of the bombing campaign, accurately targeting the facility despite its recent reinforcement — including full concrete encasement and a thick overlying layer of earth. They show that the bunker buster bombs were not only precisely on target along the length of the main suspected high explosive test chamber hall, but it is clear that the bombs successfully penetrated the encasing concrete sarcophagus into the interior given the evidence that the main blast(s) traveled outward from the interior to cause significant collateral damage in knocking down a protective defensive wall just outside the northern entrance. A small building southeast of the facility appears to have been partially destroyed by the concussion from the main bunker buster blasts. Construction of the new facility only started in May 2025, following Israel's October 2024 strike on the previous facility. During construction, satellite imagery showed the front cylindrical portion of what may have been a high explosive containment vessel (see below). We also provide background on the broader Taleghan site, which includes a location known as Taleghan 1 rooted in Iran's Amad Plan and which we have been monitoring for almost 15 years.

NEW: Detailed assessment of the Israeli strike on Taleghan 2, a site "used by the Iranian regime to advance nuclear weapons capabilities," according to the IDF. We detail the damage done to the newly constructed, bunkered facility, and nearby structures. Below is a composite image created by transparently overlaying the post-strike satellite photograph taken by Vantor on 11 March 2026 onto earlier pre-strike imagery. The overlays are designed to demonstrate the high precision of the bombing campaign, accurately targeting the facility despite its recent reinforcement — including full concrete encasement and a thick overlying layer of earth. They show that the bunker buster bombs were not only precisely on target along the length of the main suspected high explosive test chamber hall, but it is clear that the bombs successfully penetrated the encasing concrete sarcophagus into the interior given the evidence that the main blast(s) traveled outward from the interior to cause significant collateral damage in knocking down a protective defensive wall just outside the northern entrance. A small building southeast of the facility appears to have been partially destroyed by the concussion from the main bunker buster blasts. Construction of the new facility only started in May 2025, following Israel's October 2024 strike on the previous facility. During construction, satellite imagery showed the front cylindrical portion of what may have been a high explosive containment vessel (see below). We also provide background on the broader Taleghan site, which includes a location known as Taleghan 1 rooted in Iran's Amad Plan and which we have been monitoring for almost 15 years.

Inst for Science

13,832 Aufrufe • vor 6 Monaten

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

1/ Gemini 2.5 is here, and it’s our most intelligent AI model ever. Our first 2.5 model, Gemini 2.5 Pro Experimental is a state-of-the-art thinking model, leading in a wide range of benchmarks – with impressive improvements in enhanced reasoning and coding and now #1 on Arena by a significant margin. With a model this intelligent, we wanted to get it to people as quickly as possible. Find it on Google AI Studio and in the Google Gemini for Gemini Advanced users now – and in Vertex in the coming weeks. This is the start of a new era of thinking models – and we can’t wait to see where things go from here.

Sundar Pichai

864,841 Aufrufe • vor 1 Jahr

E11 Bio is excited to unveil PRISM technology for mapping brain wiring with simple light microscopes. Today, brain mapping in humans and other mammals is bottlenecked by accurate neuron tracing. PRISM uses molecular ID codes and AI to help neurons trace themselves. We discovered a new cell barcoding approach exceeding comparable methods by more than 750x. This is the heart of PRISM. We integrated this capability with microscopy and AI image analysis to automatically trace neurons at high resolution and annotate them with molecular features. This is a key advance towards economically viable brain mapping - 95% of costs stem from neuron tracing. It is also an important step towards democratizing neuron tracing for everyday neuroscience. Solving these problems is critical for curing brain disorders, building safer and human-like AI, and even simulating brain function. In our first pilot study, we acquired a unique dataset in mouse hippocampus. Barcodes improved the accuracy of tracing genetically labelled neurons by 8x – with a clear path to 100x or more. They also permit tracing across spatial gaps – essential for mitigating tissue section loss in whole-brain scaling. Using molecular annotation, we uncover an intriguing feature of synaptic organization, demonstrating how PRISM can be used for systematic discovery 🧵

E11 Bio is excited to unveil PRISM technology for mapping brain wiring with simple light microscopes. Today, brain mapping in humans and other mammals is bottlenecked by accurate neuron tracing. PRISM uses molecular ID codes and AI to help neurons trace themselves. We discovered a new cell barcoding approach exceeding comparable methods by more than 750x. This is the heart of PRISM. We integrated this capability with microscopy and AI image analysis to automatically trace neurons at high resolution and annotate them with molecular features. This is a key advance towards economically viable brain mapping - 95% of costs stem from neuron tracing. It is also an important step towards democratizing neuron tracing for everyday neuroscience. Solving these problems is critical for curing brain disorders, building safer and human-like AI, and even simulating brain function. In our first pilot study, we acquired a unique dataset in mouse hippocampus. Barcodes improved the accuracy of tracing genetically labelled neurons by 8x – with a clear path to 100x or more. They also permit tracing across spatial gaps – essential for mitigating tissue section loss in whole-brain scaling. Using molecular annotation, we uncover an intriguing feature of synaptic organization, demonstrating how PRISM can be used for systematic discovery 🧵

Andrew Payne

112,827 Aufrufe • vor 1 Jahr

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

MrNeRF

21,389 Aufrufe • vor 1 Jahr

The term "continual learning" has become overloaded if you see it as an ML problem. One classic thread is about memorization: regularization-based continual learning methods, such as EWC, MAS, and SI, estimate which parameters mattered for previous tasks and resist changing them too much. One modern thread is about adaptation: test-time training and inference-time learning methods, such as TTT, adapt part of the model on the incoming test stream before making predictions. These are sometimes discussed as separate threads. But in modern scalable architectures, I think they are better seen as complementary constraints: a model that learns quickly at test time also benefits from a mechanism for deciding what not to forget. In our #ECCV2026 paper, we study this in large-scale 4D reconstruction: how to build fast spatial memory that can adapt over long observation streams while reducing collapse and forgetting. Instead of using fully plastic test-time updates, we stabilize fast-weight adaptation with an elastic prior that balances adaptation and memory. Key ideas: - Elastic Test-Time Training: Fisher-weighted consolidation for fast-weight updates - EMA anchor weights that provide a moving reference for stability - Chunk-by-chunk inference for long 3D/4D observation streams We show that this scales across large 3D/4D pretraining settings, including both LRM-style and LVSM-style models, and improves reconstruction across benchmarks including Stereo4D, NVIDIA, and DL3DV-140. We release model checkpoints across different design choices: resolution, post-training curriculum, and whether the model uses an explicit 4DGS intermediate representation. - Homepage: - Paper: - Code: - Models: This work is co-led with Xueyang Yu, contributed by Haoyu Zhen Yuncong Yang, and advised by Michigan SLED Lab Chuang Gan.

The term "continual learning" has become overloaded if you see it as an ML problem. One classic thread is about memorization: regularization-based continual learning methods, such as EWC, MAS, and SI, estimate which parameters mattered for previous tasks and resist changing them too much. One modern thread is about adaptation: test-time training and inference-time learning methods, such as TTT, adapt part of the model on the incoming test stream before making predictions. These are sometimes discussed as separate threads. But in modern scalable architectures, I think they are better seen as complementary constraints: a model that learns quickly at test time also benefits from a mechanism for deciding what not to forget. In our #ECCV2026 paper, we study this in large-scale 4D reconstruction: how to build fast spatial memory that can adapt over long observation streams while reducing collapse and forgetting. Instead of using fully plastic test-time updates, we stabilize fast-weight adaptation with an elastic prior that balances adaptation and memory. Key ideas: - Elastic Test-Time Training: Fisher-weighted consolidation for fast-weight updates - EMA anchor weights that provide a moving reference for stability - Chunk-by-chunk inference for long 3D/4D observation streams We show that this scales across large 3D/4D pretraining settings, including both LRM-style and LVSM-style models, and improves reconstruction across benchmarks including Stereo4D, NVIDIA, and DL3DV-140. We release model checkpoints across different design choices: resolution, post-training curriculum, and whether the model uses an explicit 4DGS intermediate representation. - Homepage: - Paper: - Code: - Models: This work is co-led with Xueyang Yu, contributed by Haoyu Zhen Yuncong Yang, and advised by Michigan SLED Lab Chuang Gan.

Martin Ziqiao Ma

34,012 Aufrufe • vor 3 Monaten

I am currently on Reservist training. Here in Norway with the Royal Marine Surveillance and Reconnaissance Squadron. Dusting off some old skills and drills in the Arctic Circle. It’s -18C but still workable for insertion skills. Norway is not just a strategic ally it’s a geopolitical partnership. With Russian submarine and naval activity in the North Atlantic increasing by over 30% in the past two years we need to increasingly work together. Lunar House is our bilateral agreement with the Norwegians and it’s going from strength to strength. This is the biggest deployment of Marines to the high north in some time.

I am currently on Reservist training. Here in Norway with the Royal Marine Surveillance and Reconnaissance Squadron. Dusting off some old skills and drills in the Arctic Circle. It’s -18C but still workable for insertion skills. Norway is not just a strategic ally it’s a geopolitical partnership. With Russian submarine and naval activity in the North Atlantic increasing by over 30% in the past two years we need to increasingly work together. Lunar House is our bilateral agreement with the Norwegians and it’s going from strength to strength. This is the biggest deployment of Marines to the high north in some time.

Al Carns

91,577 Aufrufe • vor 8 Monaten

What a night! We came in full force! Huge thanks to our sweethearts and solids, especially those who travelled and flew in from the provinces just to be with us. Your love and support mean the world! There are also more block screenings organized by different groups—let’s cheer them on and show our support. See you all at the cinemas! COLOVE NOW SHOWING #PuregoldCinePanalo2025

What a night! We came in full force! Huge thanks to our sweethearts and solids, especially those who travelled and flew in from the provinces just to be with us. Your love and support mean the world! There are also more block screenings organized by different groups—let’s cheer them on and show our support. See you all at the cinemas! COLOVE NOW SHOWING #PuregoldCinePanalo2025

KDLEX INTERNATIONAL SWEETHEARTS

13,942 Aufrufe • vor 1 Jahr

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

Depth Any Video with Scalable Synthetic Data AI physicists and chemists continue to make strides in depth estimation from video. Check out this new paper featuring some impressive examples. See the thread for more details (unfortunately no code yet). Abstract: Video depth estimation has long been hindered by the scarcity of consistent and scalable ground truth data, leading to inconsistent and unreliable results. In this paper, we introduce Depth Any Video, a model that tackles the challenge through two key innovations. First, we develop a scalable synthetic data pipeline, capturing real-time video depth data from diverse game environments, yielding 40,000 video clips of 5-second duration, each with precise depth annotations. Second, we leverage the powerful priors of generative video diffusion models to handle real-world videos effectively, integrating advanced techniques such as rotary position encoding and flow matching to further enhance flexibility and efficiency. Unlike previous models, which are limited to fixed-length video sequences, our approach introduces a novel mixed-duration training strategy that handles videos of varying lengths and performs robustly across different frame rates 0 - even on single frames. At inference, we propose a depth interpolation method that enables our model to infer high-resolution video depth across sequences of up to 150 frames. Our model outperforms all previous generative depth models in terms of spatial accuracy and temporal consistency.

MrNeRF

27,428 Aufrufe • vor 2 Jahren

JUST IN: The frat boys who held up the American flag at UNC and told a pro-Palestine protester to lose some weight have had $270,000 raised for them to throw a rager. Epic 🇺🇸 In just one day, the boys are narrowing in on $300,000 and have even received a $10,000 donation from billionaire Bill Ackman. “We are overwhelmed by you glorious, Patriotic Americans who value good beer and great times. We are in contact with multiple leaders from fraternities whose members helped defend the flag, including Alpha Epsilon Pi and others, in addition to Pi Kappa Psi,” an update on the page read. Well deserved.

JUST IN: The frat boys who held up the American flag at UNC and told a pro-Palestine protester to lose some weight have had $270,000 raised for them to throw a rager. Epic 🇺🇸 In just one day, the boys are narrowing in on $300,000 and have even received a $10,000 donation from billionaire Bill Ackman. “We are overwhelmed by you glorious, Patriotic Americans who value good beer and great times. We are in contact with multiple leaders from fraternities whose members helped defend the flag, including Alpha Epsilon Pi and others, in addition to Pi Kappa Psi,” an update on the page read. Well deserved.

Collin Rugg

7,884,176 Aufrufe • vor 2 Jahren

📐Design Systems and DESIGN.md Consistency using Design Systems and DESIGN.md: ✨ Every new design automatically starts with a cohesive design system which GREATLY improves consistency (we heard you!) ✨ Edit the system, and all associated screens can be easily updated ✨ You can extract a design system from any URL ✨ Use DESIGN.md to export your design rules or import your design rules from other products (just ask your agent to create you a DESIGN.md file from your code or other context) ✨ You can start a new design by choosing from popular design systems ✨ Read more about DESIGN.md in the docs (link in thread)

📐Design Systems and DESIGN.md Consistency using Design Systems and DESIGN.md: ✨ Every new design automatically starts with a cohesive design system which GREATLY improves consistency (we heard you!) ✨ Edit the system, and all associated screens can be easily updated ✨ You can extract a design system from any URL ✨ Use DESIGN.md to export your design rules or import your design rules from other products (just ask your agent to create you a DESIGN.md file from your code or other context) ✨ You can start a new design by choosing from popular design systems ✨ Read more about DESIGN.md in the docs (link in thread)

Stitch by Google

219,386 Aufrufe • vor 6 Monaten

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

The Hidden Language of Diffusion Models paper page: tackle the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulation

AK

41,830 Aufrufe • vor 3 Jahren

We are happy to share that Sorted has raised $4.4M in seed funding 💙 The round is led by Tether and Gnosis, with participation from Movement, Angel Invest, and several angel investors including the founders of RWA.io. We started Sorted because we saw a gap nobody else was filling. Hundreds of millions of people on phones that work perfectly well, with no access to stable digital money. We decided to build for them. Today, Sorted Wallet runs across 160 countries with over 500,000 downloads. This round lets us grow in the markets we already serve, and reach the ones still waiting. To our investors, our team, and every user who found us before we found them: thank you for being part of our story 🙏 Onwards and upwards from here! Read the full announcement 👇 #Sorted #Stablecoins #FinancialInclusion #EmergingMarkets

We are happy to share that Sorted has raised $4.4M in seed funding 💙 The round is led by Tether and Gnosis, with participation from Movement, Angel Invest, and several angel investors including the founders of RWA.io. We started Sorted because we saw a gap nobody else was filling. Hundreds of millions of people on phones that work perfectly well, with no access to stable digital money. We decided to build for them. Today, Sorted Wallet runs across 160 countries with over 500,000 downloads. This round lets us grow in the markets we already serve, and reach the ones still waiting. To our investors, our team, and every user who found us before we found them: thank you for being part of our story 🙏 Onwards and upwards from here! Read the full announcement 👇 #Sorted #Stablecoins #FinancialInclusion #EmergingMarkets

Sorted

38,012 Aufrufe • vor 4 Monaten

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,062 Aufrufe • vor 1 Jahr