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.

CamCloneMaster: replicating camera movements from reference videos without needing camera parameters; based on Wan2.1-1.3B; built using a large-scale Camera Clone Dataset. Solid results.

Wildminder

9,880 subscribers

16,829 Aufrufe • vor 10 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Face shape keys based on camera angle and using grease pencil to reference

Face shape keys based on camera angle and using grease pencil to reference

Denver Jackson 🍥

61,095 Aufrufe • vor 7 Monaten

🚨Dynamic Camera Tutorial🚨 Struggling to get dynamic camera movements in your AI videos? We cracked the code! 🚀 Here's how we craft dynamic videos with stunning results using a Master Prompt Template for ChatGPT (or any other LLM) that incorporates dynamic camera movements! Creative process + examples 👇 Sound On 🔉

🚨Dynamic Camera Tutorial🚨 Struggling to get dynamic camera movements in your AI videos? We cracked the code! 🚀 Here's how we craft dynamic videos with stunning results using a Master Prompt Template for ChatGPT (or any other LLM) that incorporates dynamic camera movements! Creative process + examples 👇 Sound On 🔉

Nim

36,993 Aufrufe • vor 1 Jahr

Presenting MonoNeRF at #ICML2023 We train a generalizable NeRF from: ✅Large-scale monocular videos instead of one scene ✅No GT camera poses.📷🚫 Without per-scene optimization, the model can do view synthesis, depth estimation, camera pose estimation.

Presenting MonoNeRF at #ICML2023 We train a generalizable NeRF from: ✅Large-scale monocular videos instead of one scene ✅No GT camera poses.📷🚫 Without per-scene optimization, the model can do view synthesis, depth estimation, camera pose estimation.

Xiaolong Wang

36,578 Aufrufe • vor 3 Jahren

Introducing ✨Posed DROID✨, results of our efforts at automatic post-hoc calibration of a large-scale robotics manipulation dataset. We provide: 🤖 ~36k calibrated episodes with good quality extrinsic calibration 🦾 ~24k calibrated multi-view episodes with good-quality multi-view camera calibration ✅ Quality assessment metrics for all provided camera poses To achieve this, we utilize: 1️⃣ Auto Segment Anything (SAM) based filtering (Camera-to-Base Calibration) 2️⃣ Tuned CtRNet-X for bringing in additional cams (Camera-to-Base Calibration) 3️⃣ Pretrained DUST3R with depth-based pose optimization (Camera-to-Camera Calibration) Try it out at: Learn more at: 🌐 arXiv: 📄 Blog: 🧵 1/n

Introducing ✨Posed DROID✨, results of our efforts at automatic post-hoc calibration of a large-scale robotics manipulation dataset. We provide: 🤖 ~36k calibrated episodes with good quality extrinsic calibration 🦾 ~24k calibrated multi-view episodes with good-quality multi-view camera calibration ✅ Quality assessment metrics for all provided camera poses To achieve this, we utilize: 1️⃣ Auto Segment Anything (SAM) based filtering (Camera-to-Base Calibration) 2️⃣ Tuned CtRNet-X for bringing in additional cams (Camera-to-Base Calibration) 3️⃣ Pretrained DUST3R with depth-based pose optimization (Camera-to-Camera Calibration) Try it out at: Learn more at: 🌐 arXiv: 📄 Blog: 🧵 1/n

Zubair Irshad

13,585 Aufrufe • vor 1 Jahr

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

ViPE: Video Pose Engine for 3D Geometric Perception Contributions: • A robust and efficient framework, ViPE, for estimating camera parameters and dense depth from diverse, in-the-wild videos. • A system design that integrates the strengths of classical SLAM (efficiency, scalability) and learned models (robustness), with key improvements in efficiency, dynamic object handling, and depth quality over prior work. • A large-scale dataset of annotated videos, created using ViPE, to facilitate future research in 3D computer vision.

MrNeRF

42,635 Aufrufe • vor 1 Jahr

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, *metric* 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Introducing 👀Stereo4D👀 A method for mining 4D from internet stereo videos. It enables large-scale, high-quality, dynamic, metric 3D reconstructions, with camera poses and long-term 3D motion trajectories. We used Stereo4D to make a dataset of over 100k real-world 4D scenes.

Linyi Jin

94,588 Aufrufe • vor 1 Jahr

🚨 Grok Imagine Video 1.5 drops on fal! Turn a prompt or reference frame into polished video in seconds Fluid camera work, coherent scenes and output that holds up on close inspection Built for creators who want premium results without a heavy pipeline

🚨 Grok Imagine Video 1.5 drops on fal! Turn a prompt or reference frame into polished video in seconds Fluid camera work, coherent scenes and output that holds up on close inspection Built for creators who want premium results without a heavy pipeline

fal

41,381 Aufrufe • vor 3 Monaten

4. Elai / Elai.io Create AI videos from just text. Build customized AI videos with a presenter in minutes without using a camera, studio and a green screen 🔗

4. Elai / Elai.io Create AI videos from just text. Build customized AI videos with a presenter in minutes without using a camera, studio and a green screen 🔗

Angry Tom

50,592 Aufrufe • vor 3 Jahren

Still struggling to create cinematic camera movements? 🎥 No more writing complicated camera prompts. Just pick a shot you want, and OiiOii AI brings cinematic camera motions to life instantly. From dolly shots to dramatic zooms, create professional-looking videos with one click. Your cinematic shots, made simple.

Still struggling to create cinematic camera movements? 🎥 No more writing complicated camera prompts. Just pick a shot you want, and OiiOii AI brings cinematic camera motions to life instantly. From dolly shots to dramatic zooms, create professional-looking videos with one click. Your cinematic shots, made simple.

OiiOii AI

38,480 Aufrufe • vor 1 Monat

Levilente02, a Forza modder, made a Need for Speed camera mod for Forza Horizon 6. The camera mod is based on the action camera from the 32-y/o franchise's reboot era; 2015, Payback, Heat, and Unbound. #ForzaHorizon6 #FH6 #ForzaShare #NeedforSpeed #NFS

Levilente02, a Forza modder, made a Need for Speed camera mod for Forza Horizon 6. The camera mod is based on the action camera from the 32-y/o franchise's reboot era; 2015, Payback, Heat, and Unbound. #ForzaHorizon6 #FH6 #ForzaShare #NeedforSpeed #NFS

Alan

28,660 Aufrufe • vor 1 Monat

360 camera-based Gaussian Splatting is often highlighted for large-scale scans, but for around 2m × 2m objects, I’ve found it gives a higher success rate with my setup than 3D scan apps for smartphone. Definitely worth trying. If you’re interested, check out the reference below.

360 camera-based Gaussian Splatting is often highlighted for large-scale scans, but for around 2m × 2m objects, I’ve found it gives a higher success rate with my setup than 3D scan apps for smartphone. Definitely worth trying. If you’re interested, check out the reference below.

Takashi Yoshinaga

14,598 Aufrufe • vor 5 Monaten

Late night experiment. I built a demo that generates 3D environments from images into 3DGS, then uses them as a spatial reference for directing real-time AR camera movements. The capture is then run through Seedance 2.0 for the final output. all running on the web via three.js↓

Late night experiment. I built a demo that generates 3D environments from images into 3DGS, then uses them as a spatial reference for directing real-time AR camera movements. The capture is then run through Seedance 2.0 for the final output. all running on the web via three.js↓

Ian Curtis

28,168 Aufrufe • vor 2 Monaten

The plot thickens. 🕵️ Use Gemini 2.5 Pro in the Google Gemini to turn random videos from your camera roll into a dramatic narrative. Try it yourself: 1️⃣ Go to Gemini and select “2.5 Pro” from the model dropdown. 2️⃣ Tap the plus icon and upload three videos from your camera roll. (Pro/Ultra subscribers, try using your Veo creations! 🎥) 3️⃣ Ask Gemini to write a short story based on the videos. Here’s our prompt to get you started: “Come up with a premise for an epic adventure based on these videos.”

The plot thickens. 🕵️ Use Gemini 2.5 Pro in the Google Gemini to turn random videos from your camera roll into a dramatic narrative. Try it yourself: 1️⃣ Go to Gemini and select “2.5 Pro” from the model dropdown. 2️⃣ Tap the plus icon and upload three videos from your camera roll. (Pro/Ultra subscribers, try using your Veo creations! 🎥) 3️⃣ Ask Gemini to write a short story based on the videos. Here’s our prompt to get you started: “Come up with a premise for an epic adventure based on these videos.”

Google

164,567 Aufrufe • vor 1 Jahr

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

Progressively Optimized Local Radiance Fields for Robust View Synthesis paper page: present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

AK

140,624 Aufrufe • vor 3 Jahren

Streaming Smart Glasses Camera to a Quest 3 in WebXR A-Frame Using our Wearables SDK, we’re able to stream camera data from the Omi AI Omi Glass (based on the Seeed Studio XIAO ESP32-S3 Sense running custom firmware) to the Quest 3 over WebSockets in the Oculus Browser

Streaming Smart Glasses Camera to a Quest 3 in WebXR A-Frame Using our Wearables SDK, we’re able to stream camera data from the Omi AI Omi Glass (based on the Seeed Studio XIAO ESP32-S3 Sense running custom firmware) to the Quest 3 over WebSockets in the Oculus Browser

Brilliant Wear

18,572 Aufrufe • vor 8 Monaten

Reference Hub. Creativity Unleashed. Now live. The world’s first AI video reference-based creation community 🎬 A new creative paradigm: powered by Vidu’s reference-based video generation, creators can select from different reference types to produce professional-quality videos 🌏 8 reference types: professional-level video results without complex prompting 🎞 Making professional output effortless: stable, high-quality results with greater efficiency #YesVidu #Viduai #Creativity #ReferenceHub

Reference Hub. Creativity Unleashed. Now live. The world’s first AI video reference-based creation community 🎬 A new creative paradigm: powered by Vidu’s reference-based video generation, creators can select from different reference types to produce professional-quality videos 🌏 8 reference types: professional-level video results without complex prompting 🎞 Making professional output effortless: stable, high-quality results with greater efficiency #YesVidu #Viduai #Creativity #ReferenceHub

Vidu AI

14,942 Aufrufe • vor 7 Monaten

Ropedia Xperience-10M is out on Hugging Face a large-scale egocentric multimodal dataset of human experience for embodied AI, robotics, world models, and spatial intelligence It contains 10 million experiences (interaction) and 10,000 hours of synchronized first-person recordings with six video streams, audio, stereo depth, camera pose, hand mocap, full-body mocap, IMU, and hierarchical language annotations dataset:

Ropedia Xperience-10M is out on Hugging Face a large-scale egocentric multimodal dataset of human experience for embodied AI, robotics, world models, and spatial intelligence It contains 10 million experiences (interaction) and 10,000 hours of synchronized first-person recordings with six video streams, audio, stereo depth, camera pose, hand mocap, full-body mocap, IMU, and hierarchical language annotations dataset:

AK

10,621 Aufrufe • vor 5 Monaten

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking paper page: introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework, for the training and evaluation of long-term fine-grained tracking algorithms. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. Toward the goal of naturalism, we animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos. We create combinatorial diversity by randomizing character appearance, motion profiles, materials, lighting, 3D assets, and atmospheric effects. Our dataset currently includes 104 videos, averaging 2,000 frames long, with orders of magnitude more correspondence annotations than prior work. We show that existing methods can be trained from scratch in our dataset and outperform the published variants. Finally, we introduce modifications to the PIPs point tracking method, greatly widening its temporal receptive field, which improves its performance on PointOdyssey as well as on two real-world benchmarks.

AK

122,567 Aufrufe • vor 3 Jahren

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.

Superman

1,454,964 Aufrufe • vor 1 Monat

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.

Yasir Ai

254,504 Aufrufe • vor 1 Monat