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。

LGTM from Apple: 4K feed-forward 3D Gaussian Splatting. instant 4K 3D scenes without massive GPUs.. - predicts a few lightweight 3D shapes, wraps them in ultra-high-res 2D textures. - low Memory usage You take two normal photos of a room. Instantly walk around it in flawless 3D.

Wildminder

11,120 subscribers

46,458 次观看 • 5 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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

21,346 次观看 • 1 年前

3D $ANIME ? Using 3D in anime or a complete series in 3D style, how does this affect the anime industry? Probably the most hated anime after which people hated 3D in anime was Berserk in 2016, it was really terrible, but 3D in anime is no longer what it was in 2010-20. Let's look at the pros and cons of 3D in anime and what series can be called good 3D anime Pros of 3D Animation: 🟢Dynamic camera angles & smooth motion 🟢Saves time & production costs 🟢Consistent character proportions Cons of 3D Animation: 🔴Can look stiff or "plastic" 🔴Limited facial expressions 🔴Often disliked by traditional anime fans Top 3D $ANIME series in my opinion: 🔵Houseki no Kuni – stunning visuals & fluid animation 🔵Dorohedoro – dark, gritty style perfectly fits CGI 🔵Beastars – expressive character animation 🔵Trigun: Stampede – cinematic action & high-quality CGI The best studio that combines 2D and 3D well is, I think, Ufotable Ufotable blends 2D & 3D seamlessly: 🟡3D backgrounds + 2D character animation 🟡Anime-style shading makes 3D look hand-drawn 🟡Frame-by-frame touch-ups for smooth motion 🟡Mixing 2D effects (fire, water) with 3D for impact Example: "Demon Slayer" – epic battle scenes like Tanjiro’s Water Breathing, using 3D camera movement while preserving 2D aesthetics. Which 3D $ANIME impressed you the most?

3D $ANIME ? Using 3D in anime or a complete series in 3D style, how does this affect the anime industry? Probably the most hated anime after which people hated 3D in anime was Berserk in 2016, it was really terrible, but 3D in anime is no longer what it was in 2010-20. Let's look at the pros and cons of 3D in anime and what series can be called good 3D anime Pros of 3D Animation: 🟢Dynamic camera angles & smooth motion 🟢Saves time & production costs 🟢Consistent character proportions Cons of 3D Animation: 🔴Can look stiff or "plastic" 🔴Limited facial expressions 🔴Often disliked by traditional anime fans Top 3D $ANIME series in my opinion: 🔵Houseki no Kuni – stunning visuals & fluid animation 🔵Dorohedoro – dark, gritty style perfectly fits CGI 🔵Beastars – expressive character animation 🔵Trigun: Stampede – cinematic action & high-quality CGI The best studio that combines 2D and 3D well is, I think, Ufotable Ufotable blends 2D & 3D seamlessly: 🟡3D backgrounds + 2D character animation 🟡Anime-style shading makes 3D look hand-drawn 🟡Frame-by-frame touch-ups for smooth motion 🟡Mixing 2D effects (fire, water) with 3D for impact Example: "Demon Slayer" – epic battle scenes like Tanjiro’s Water Breathing, using 3D camera movement while preserving 2D aesthetics. Which 3D $ANIME impressed you the most?

Kvintestar⛩️ Anime Artist

15,599 次观看 • 1 年前

You need to take 3D AI seriously now! Rodin AI lets you generate a high-poly 3D mesh of your product using just five images from different angles. Once done, you can render your product from any perspective you want. Try it for free. Link in comments.

You need to take 3D AI seriously now! Rodin AI lets you generate a high-poly 3D mesh of your product using just five images from different angles. Once done, you can render your product from any perspective you want. Try it for free. Link in comments.

el.cine

90,228 次观看 • 1 年前

Combining the explicit control of 3D software with the creativity of generative AI models is a promising yet underrated workflow. Build your 3D scenes procedurally by describing them in natural language, then take them all the way with your image & video models of choice. Tools like intangible are built around such a workflow so you don't need to duct-tape apps together. Pretty cool!

Combining the explicit control of 3D software with the creativity of generative AI models is a promising yet underrated workflow. Build your 3D scenes procedurally by describing them in natural language, then take them all the way with your image & video models of choice. Tools like intangible are built around such a workflow so you don't need to duct-tape apps together. Pretty cool!

Bilawal Sidhu

37,629 次观看 • 1 年前

Timelapse video of a FTN 300BO Form 1 suppressor being 3d printed in PA6-CF-20 filament. So, serious question... Why haven't you filed your form 1 and 3d printed your own hearing protection? Cost of materials is less than $15 (not including the 3d printer) Private citizens can legally purchase & possess silencers in 42 (yes.. fourty two) states without a permit, and in other states with legal permission. So for under $10, a little paperwork (done and approved BEFORE you begin to make it), and a few minutes assembling & engraving you are done If not now, when?

Timelapse video of a FTN 300BO Form 1 suppressor being 3d printed in PA6-CF-20 filament. So, serious question... Why haven't you filed your form 1 and 3d printed your own hearing protection? Cost of materials is less than $15 (not including the 3d printer) Private citizens can legally purchase & possess silencers in 42 (yes.. fourty two) states without a permit, and in other states with legal permission. So for under $10, a little paperwork (done and approved BEFORE you begin to make it), and a few minutes assembling & engraving you are done If not now, when?

Wny Poker

106,362 次观看 • 7 个月前

🚨Game Introduction🚨 After a failed launch of my first Indiegame, I decided to take the shark transform mechanic from 2D to 3D... Its about a month in developement but stopped for now! Would you play it? 👀 #indiegame #metroidvania #gamedev #Indiedev

🚨Game Introduction🚨 After a failed launch of my first Indiegame, I decided to take the shark transform mechanic from 2D to 3D... Its about a month in developement but stopped for now! Would you play it? 👀 #indiegame #metroidvania #gamedev #Indiedev

Zoroarts 🦈 Paddle Paddle Paddle OUT NOW

36,571 次观看 • 3 年前

🚀🌍🚀 Echo-2 is live! It generates high-quality physically grounded 3D scenes instead of just pixels. Check out the open demo to create and explore worlds in real-time! I gave it a picture from my Himalayas trek—it handles the massive scale range really well! 🏔️🌍

🚀🌍🚀 Echo-2 is live! It generates high-quality physically grounded 3D scenes instead of just pixels. Check out the open demo to create and explore worlds in real-time! I gave it a picture from my Himalayas trek—it handles the massive scale range really well! 🏔️🌍

David Novotny

11,435 次观看 • 4 个月前

New vibecode project: 3D world generation on your phone ✨ Take a photo of a room or space, and transform it into a new style. Then generate a world you can explore. Made in Cursor using two new APIs - Flux.2 Klein (BlackForestLabsAI - Unofficial) and Marble (World Labs). How it works 👇

New vibecode project: 3D world generation on your phone ✨ Take a photo of a room or space, and transform it into a new style. Then generate a world you can explore. Made in Cursor using two new APIs - Flux.2 Klein (BlackForestLabsAI - Unofficial) and Marble (World Labs). How it works 👇

Justine Moore

42,665 次观看 • 7 个月前

$🚨 SCIENTISTS JUST USED A FEMTOSECOND LASER FLASH TO PUSH MAGNETISM INTO AN ENTIRELY NEW 3D STATE. In a fraction of a quadrillionth of a second, a burst of ultra-fast laser light forced magnetic structures to twist into complex three-dimensional shapes that normally never exist in equilibrium. Why this matters: Modern tech runs on magnetism hard drives, memory, quantum devices, and future spintronic computers. But magnetism has always been manipulated relatively slowly. This experiment changed the magnetic order in quadrillionths of a second. The deeper implication is staggering: Matter may be hiding entire families of temporary 3D magnetic states that only appear when you push it faster than it can relax. Reality itself behaves differently under extreme time compression. That could unlock: ultra-fast magnetic memory light-controlled spintronic computing entirely new quantum materials information storage that works at the speed of light The future of technology may not come from making electronics smaller… but from driving matter into hidden states nature almost never shows us. What happens when we learn to control these fleeting 3D magnetic landscapes on demand?$

🚨 SCIENTISTS JUST USED A FEMTOSECOND LASER FLASH TO PUSH MAGNETISM INTO AN ENTIRELY NEW 3D STATE. In a fraction of a quadrillionth of a second, a burst of ultra-fast laser light forced magnetic structures to twist into complex three-dimensional shapes that normally never exist in equilibrium. Why this matters: Modern tech runs on magnetism hard drives, memory, quantum devices, and future spintronic computers. But magnetism has always been manipulated relatively slowly. This experiment changed the magnetic order in quadrillionths of a second. The deeper implication is staggering: Matter may be hiding entire families of temporary 3D magnetic states that only appear when you push it faster than it can relax. Reality itself behaves differently under extreme time compression. That could unlock: ultra-fast magnetic memory light-controlled spintronic computing entirely new quantum materials information storage that works at the speed of light The future of technology may not come from making electronics smaller… but from driving matter into hidden states nature almost never shows us. What happens when we learn to control these fleeting 3D magnetic landscapes on demand?

TheNewPhysics

22,740 次观看 • 3 个月前

China just dropped an open source model that turns any phone into a 3D scanner you point it at a room and walk through it the whole space builds itself into a 3D point cloud in real time as the camera moves, no LiDAR and no depth sensor anywhere it held a full 13 minute walkthrough at 25,000 frames without the map drifting or collapsing > ~20 fps on a single GPU > works indoors and outdoors from plain footage > the scan normally needs a $50,000 rig and a technician > Apache 2.0 and runs fully offline on your machine repo in the reply

China just dropped an open source model that turns any phone into a 3D scanner you point it at a room and walk through it the whole space builds itself into a 3D point cloud in real time as the camera moves, no LiDAR and no depth sensor anywhere it held a full 13 minute walkthrough at 25,000 frames without the map drifting or collapsing > ~20 fps on a single GPU > works indoors and outdoors from plain footage > the scan normally needs a $50,000 rig and a technician > Apache 2.0 and runs fully offline on your machine repo in the reply

savip

104,123 次观看 • 1 个月前

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.

MrNeRF

50,571 次观看 • 10 个月前

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

This is some quietly impressive work on making video world models actually controllable in 4D space. VerseCrafter lets you take an input image, use something like Blender to animate the 3D camera path and object trajectories, then uses that to condition generation. Scribbling in 2D feels so crude in comparison. The authors represent everything in a shared 4D world state - static background as a point cloud, moving objects as 3D gaussian trajectories. The gaussians are an interesting choice because they capture position, shape, and orientation probabilistically rather than forcing rigid bounding boxes or category specific models like SMPL-X for human bodies. They bolt this onto frozen Wan2.1 with a lightweight adapter, so they get a strong video prior. They also built a pipeline to auto extract 4D annotations from real world videos to train this puppy. It doesn't look sexy yet, but IMO this is the interface video world models need - actual 3D authoring tools to exert control rather than crude scribbles and prompt incantations.

Bilawal Sidhu

26,017 次观看 • 7 个月前

Two weeks ago I fixed one of my teeth with algorithms I wrote a couple of years ago! I got hooked by 3D scanning when I started to work for a software shop in Zurich that was programming 3D computational geometry algorithms for denture scanning to produce crowns (and more). Back then, a typical reconstruction pipeline was like: scan the patient’s teeth using an intraoral scanner, reconstruct the surface mesh, design the restoration digitally, and finally mill the crown out of ceramic. We were working mostly with point clouds and meshes, but it wasn’t just math, it was craftsmanship translated into a digital process. Every micron mattered. You could literally see how a good algorithm meant a better fit in someone’s mouth. Gaussian Splatting isn’t about surface reconstruction, it’s about appearance reconstruction. It doesn’t care about explicit topology, it captures how light interacts with the scene. In a sense, it’s the opposite philosophy of the dental world: instead of modeling what the object is, it models how the object looks. 3D Gaussian Splatting enables applications like training self driving cars, teaching robots to understand their environment, creating virtual worlds, or monitoring real sites. It represents scenes as millions of small Gaussians rendered in real time without the need for meshes or textures. Coming from a world where precision geometry was everything, this shift felt natural. It’s still about reconstruction, but with a different goal: not manufacturing a perfect object, but reproducing how the world actually looks. Two weeks ago I got my first dental crown, made with the same software, reconstruction algorithms, and Swiss precision I once helped develop. I haven’t worked there in two years, but sitting in that chair and seeing the process from the other side was a proud moment. It reminded me why I love this field.

Two weeks ago I fixed one of my teeth with algorithms I wrote a couple of years ago! I got hooked by 3D scanning when I started to work for a software shop in Zurich that was programming 3D computational geometry algorithms for denture scanning to produce crowns (and more). Back then, a typical reconstruction pipeline was like: scan the patient’s teeth using an intraoral scanner, reconstruct the surface mesh, design the restoration digitally, and finally mill the crown out of ceramic. We were working mostly with point clouds and meshes, but it wasn’t just math, it was craftsmanship translated into a digital process. Every micron mattered. You could literally see how a good algorithm meant a better fit in someone’s mouth. Gaussian Splatting isn’t about surface reconstruction, it’s about appearance reconstruction. It doesn’t care about explicit topology, it captures how light interacts with the scene. In a sense, it’s the opposite philosophy of the dental world: instead of modeling what the object is, it models how the object looks. 3D Gaussian Splatting enables applications like training self driving cars, teaching robots to understand their environment, creating virtual worlds, or monitoring real sites. It represents scenes as millions of small Gaussians rendered in real time without the need for meshes or textures. Coming from a world where precision geometry was everything, this shift felt natural. It’s still about reconstruction, but with a different goal: not manufacturing a perfect object, but reproducing how the world actually looks. Two weeks ago I got my first dental crown, made with the same software, reconstruction algorithms, and Swiss precision I once helped develop. I haven’t worked there in two years, but sitting in that chair and seeing the process from the other side was a proud moment. It reminded me why I love this field.

MrNeRF

290,257 次观看 • 10 个月前

2023 was the year of AI avatars 2024 was the year of AI photos 2025 was the year of AI videos And I think it's becoming clear now that 2026 will be the year of AI world models Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt In turn these 2d images can then be generated by AI too So soon you can generate fully explorable virtual 3d worlds based on your own imagination Next will be figuring out how to make those worlds interactive This is World Labs (unaffiliated, but I like it) As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now) Very exciting time again!

2023 was the year of AI avatars 2024 was the year of AI photos 2025 was the year of AI videos And I think it's becoming clear now that 2026 will be the year of AI world models Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt In turn these 2d images can then be generated by AI too So soon you can generate fully explorable virtual 3d worlds based on your own imagination Next will be figuring out how to make those worlds interactive This is World Labs (unaffiliated, but I like it) As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now) Very exciting time again!

@levelsio

584,511 次观看 • 11 个月前

In the summer of 2023, I cold emailed Jensen Huang and asked to capture a NeRF of him at SIGGRAPH. He responded in about an hour and said yes. A radiance field is, in the simplest terms, akin to a 3D photograph. A moment in time, so completely reconstructed that you can move through it and see it from angles the original cameras never occupied. NeRFs were the original method. Gaussian splatting, which debuted at that same SIGGRAPH, has since become the dominant form of radiance field. I called my late friend James, who told me we needed to begin practicing immediately. We ran capture after capture for weeks until we consistently got the capture time down to ~30 seconds with one camera. Later, in a hallway at the LA Convention Center during SIGGRAPH, I captured the portrait you're seeing now, a full 360° gaussian splat of Jensen, rendered here as a 2D flythrough. Afterward, I continued the conversation with him and members of his team to make the case for radiance fields as a foundational representation for imaging. To my surprise, they listened. Three years later, NVIDIA has several works, including NuRec, fVDB, 3DGRUT, and gsplat all utilizing radiance fields. The landscape has evolved enough that the reasoning is obvious. Gaussian splatting has begun to ship across some of the world’s largest industries, including autonomous vehicles, AEC, geospatial, media and entertainment, robotics, e-commerce, hospitality. It’s become clear that lifelike 3D is here to stay. And yet I think we will look back and be disappointed by how late we started taking 3D portraits of the people around us, just like how we have sparse 2D photos of our grandparents and great grandparents. We have billions of photographs of the people we know and love, but almost no radiance fields of them. I'll be returning to SIGGRAPH in LA where this was initially captured three years ago, with the landscape looking significantly different. Radiance fields are more under deployed than ever relative to what they can do. I'm excited for the future of imaging, and for 2D to transition into 3D. I have a few things up my sleeve that I think will make that case plainly.

In the summer of 2023, I cold emailed Jensen Huang and asked to capture a NeRF of him at SIGGRAPH. He responded in about an hour and said yes. A radiance field is, in the simplest terms, akin to a 3D photograph. A moment in time, so completely reconstructed that you can move through it and see it from angles the original cameras never occupied. NeRFs were the original method. Gaussian splatting, which debuted at that same SIGGRAPH, has since become the dominant form of radiance field. I called my late friend James, who told me we needed to begin practicing immediately. We ran capture after capture for weeks until we consistently got the capture time down to ~30 seconds with one camera. Later, in a hallway at the LA Convention Center during SIGGRAPH, I captured the portrait you're seeing now, a full 360° gaussian splat of Jensen, rendered here as a 2D flythrough. Afterward, I continued the conversation with him and members of his team to make the case for radiance fields as a foundational representation for imaging. To my surprise, they listened. Three years later, NVIDIA has several works, including NuRec, fVDB, 3DGRUT, and gsplat all utilizing radiance fields. The landscape has evolved enough that the reasoning is obvious. Gaussian splatting has begun to ship across some of the world’s largest industries, including autonomous vehicles, AEC, geospatial, media and entertainment, robotics, e-commerce, hospitality. It’s become clear that lifelike 3D is here to stay. And yet I think we will look back and be disappointed by how late we started taking 3D portraits of the people around us, just like how we have sparse 2D photos of our grandparents and great grandparents. We have billions of photographs of the people we know and love, but almost no radiance fields of them. I'll be returning to SIGGRAPH in LA where this was initially captured three years ago, with the landscape looking significantly different. Radiance fields are more under deployed than ever relative to what they can do. I'm excited for the future of imaging, and for 2D to transition into 3D. I have a few things up my sleeve that I think will make that case plainly.

Radiance Fields

18,084 次观看 • 2 个月前

From tying my laces to landing the perfect trick. Created with Gpt Image 2 + Seedance 2.0 on WaveSpeedAI Prompt: Global Character Consistency Reference Character: A teenage boy (16–18 years old) with messy curly black hair, expressive blue eyes, a slim athletic build, wearing an oversized mustard-yellow T-shirt, navy shorts, white crew socks, and white sneakers. Maintain the exact same face, hairstyle, clothing, body proportions, colors, and ultra-realistic Pixar-inspired 3D style consistently across every scene. Scene 1 (0–2s) — Bedroom The teenage boy sits on the edge of his bed in a cozy bedroom during golden sunrise, tying his white sneakers. Warm sunlight streams through the window, posters decorate the walls, cinematic lighting, shallow depth of field, slow push-in camera, ultra-realistic Pixar-inspired 3D animation. Scene 2 (2–4s) — Final Preparation Close-up of the boy tightening his shoelaces with a determined expression. Soft golden morning light, realistic fabric textures, cinematic depth of field, smooth handheld camera movement, ultra-realistic Pixar-inspired 3D animation. Scene 3 (4–6s) — Leaving Home The boy walks out of his suburban home holding a skateboard. Warm golden-hour sunlight, long shadows across the sidewalk, peaceful neighborhood, cinematic low-angle tracking shot, ultra-realistic Pixar-inspired 3D animation. Scene 4 (6–8s) — Walking to the Skate Park The boy confidently walks down the street carrying his skateboard. Sunlight filters through the trees with subtle lens flares, smooth cinematic tracking shot, realistic environment, ultra-realistic Pixar-inspired 3D animation. Scene 5 (8–10s) — Skate Park Ride The teenage boy rides his skateboard through a colorful graffiti-covered skate park. Dynamic follow camera, energetic movement, bright cinematic lighting, realistic motion blur, ultra-realistic Pixar-inspired 3D animation. Scene 6 (10–12s) — Ollie Jump The boy performs a high skateboard ollie over a graffiti ramp. Dramatic low-angle shot, city skyline in the background, realistic physics, cinematic slow motion, ultra-realistic Pixar-inspired 3D animation. Scene 7 (12–14s) — Rooftop Sunset The boy stands on a rooftop overlooking the city skyline at sunset with his back facing the camera. Warm orange and purple sky, gentle wind moving his shirt, cinematic wide shot, emotional atmosphere, ultra-realistic Pixar-inspired 3D animation. Scene 8 (14–15s) — Emotional Close-up Extreme close-up of the boy's face. His glowing blue eyes reflect the sunset while a gentle breeze moves his curly hair. Warm golden light, shallow depth of field, emotional cinematic expression, ultra-realistic Pixar-inspired 3D animation, 8K. Style Ultra-realistic Pixar-inspired 3D animation, cinematic lighting, golden hour, volumetric sunlight, smooth camera movement, shallow depth of field, realistic textures, premium color grading, consistent character identity, 8K.

From tying my laces to landing the perfect trick. Created with Gpt Image 2 + Seedance 2.0 on WaveSpeedAI Prompt: Global Character Consistency Reference Character: A teenage boy (16–18 years old) with messy curly black hair, expressive blue eyes, a slim athletic build, wearing an oversized mustard-yellow T-shirt, navy shorts, white crew socks, and white sneakers. Maintain the exact same face, hairstyle, clothing, body proportions, colors, and ultra-realistic Pixar-inspired 3D style consistently across every scene. Scene 1 (0–2s) — Bedroom The teenage boy sits on the edge of his bed in a cozy bedroom during golden sunrise, tying his white sneakers. Warm sunlight streams through the window, posters decorate the walls, cinematic lighting, shallow depth of field, slow push-in camera, ultra-realistic Pixar-inspired 3D animation. Scene 2 (2–4s) — Final Preparation Close-up of the boy tightening his shoelaces with a determined expression. Soft golden morning light, realistic fabric textures, cinematic depth of field, smooth handheld camera movement, ultra-realistic Pixar-inspired 3D animation. Scene 3 (4–6s) — Leaving Home The boy walks out of his suburban home holding a skateboard. Warm golden-hour sunlight, long shadows across the sidewalk, peaceful neighborhood, cinematic low-angle tracking shot, ultra-realistic Pixar-inspired 3D animation. Scene 4 (6–8s) — Walking to the Skate Park The boy confidently walks down the street carrying his skateboard. Sunlight filters through the trees with subtle lens flares, smooth cinematic tracking shot, realistic environment, ultra-realistic Pixar-inspired 3D animation. Scene 5 (8–10s) — Skate Park Ride The teenage boy rides his skateboard through a colorful graffiti-covered skate park. Dynamic follow camera, energetic movement, bright cinematic lighting, realistic motion blur, ultra-realistic Pixar-inspired 3D animation. Scene 6 (10–12s) — Ollie Jump The boy performs a high skateboard ollie over a graffiti ramp. Dramatic low-angle shot, city skyline in the background, realistic physics, cinematic slow motion, ultra-realistic Pixar-inspired 3D animation. Scene 7 (12–14s) — Rooftop Sunset The boy stands on a rooftop overlooking the city skyline at sunset with his back facing the camera. Warm orange and purple sky, gentle wind moving his shirt, cinematic wide shot, emotional atmosphere, ultra-realistic Pixar-inspired 3D animation. Scene 8 (14–15s) — Emotional Close-up Extreme close-up of the boy's face. His glowing blue eyes reflect the sunset while a gentle breeze moves his curly hair. Warm golden light, shallow depth of field, emotional cinematic expression, ultra-realistic Pixar-inspired 3D animation, 8K. Style Ultra-realistic Pixar-inspired 3D animation, cinematic lighting, golden hour, volumetric sunlight, smooth camera movement, shallow depth of field, realistic textures, premium color grading, consistent character identity, 8K.

Calira

21,181 次观看 • 1 个月前

Speaking of Dreams.. still kinda crazy to me how perfect of a match a tool like that is for generative AI workflows. Intuitive game engine/creative sandbox that allows you to build almost anything, running underneath a Gen AI render. Sculpting, painting, interacting with your two hands in 3d space, here using two move controllers which by now is tech from 2010. I haven't seen ANY way to interact with 3d that allows for the same fast and intuitive sculpting without forcing you to wear a VR headset. I made this scene a few years ago in 2 and a half hour or so as part of a 1 scene pr. episode of The Last of Us, and ran it through a combo of Runway and Sora to get to this result.

Speaking of Dreams.. still kinda crazy to me how perfect of a match a tool like that is for generative AI workflows. Intuitive game engine/creative sandbox that allows you to build almost anything, running underneath a Gen AI render. Sculpting, painting, interacting with your two hands in 3d space, here using two move controllers which by now is tech from 2010. I haven't seen ANY way to interact with 3d that allows for the same fast and intuitive sculpting without forcing you to wear a VR headset. I made this scene a few years ago in 2 and a half hour or so as part of a 1 scene pr. episode of The Last of Us, and ran it through a combo of Runway and Sora to get to this result.

Martin Nebelong

19,510 次观看 • 11 个月前

A magical transformation where dark luxury meets elegance The scorpion turns into a stunning jeweled stiletto creating a truly unique fashion moment. Made With Seedance 2.0 Prompt: A close-up vertical shot in 4K resolution depicting a magical transformation. A woman's bare foot steps down onto a large, ornate scorpion made of polished black obsidian, dark red rubies, and gold metal accents resting on a polished marble floor. As her foot touches it, the metallic ruby scorpion seamlessly morphs, wraps around her foot, and transforms into a luxury high-heeled shoe and anklet. The scorpion's tail curves around her ankle into a gem-studded strap, its claws form the pointed toe box, and its body shapes into a sleek, jeweled stiletto heel. Cinematic lighting, photorealistic, 3D render, luxury fashion aesthetic, rich depth of field, bright sunlight filtering through a grand greenhouse palace in the background, 8k ultra-detailed.

A magical transformation where dark luxury meets elegance The scorpion turns into a stunning jeweled stiletto creating a truly unique fashion moment. Made With Seedance 2.0 Prompt: A close-up vertical shot in 4K resolution depicting a magical transformation. A woman's bare foot steps down onto a large, ornate scorpion made of polished black obsidian, dark red rubies, and gold metal accents resting on a polished marble floor. As her foot touches it, the metallic ruby scorpion seamlessly morphs, wraps around her foot, and transforms into a luxury high-heeled shoe and anklet. The scorpion's tail curves around her ankle into a gem-studded strap, its claws form the pointed toe box, and its body shapes into a sleek, jeweled stiletto heel. Cinematic lighting, photorealistic, 3D render, luxury fashion aesthetic, rich depth of field, bright sunlight filtering through a grand greenhouse palace in the background, 8k ultra-detailed.

Julia

394,618 次观看 • 4 天前

Human3R: Everyone Everywhere All at Once Note: I recorded the video from the interactive demo on their project page (linked in the comment below). Abstract (excerpt): Human3R jointly recovers global multi-person SMPL-X bodies ("everyone"), dense 3D scenes ("everywhere"), and camera trajectories in a single forward pass ("all-at-once"). Our method builds upon the 4D online reconstruction model CUT3R and uses parameter-efficient visual prompt tuning to preserve CUT3R's rich spatiotemporal priors while enabling direct readout of multiple SMPL-X bodies. Human3R is a unified model that eliminates heavy dependencies and iterative refinement. After being trained on the relatively small-scale synthetic dataset BEDLAM for just one day on one GPU, it achieves superior performance with remarkable efficiency: it reconstructs multiple humans in a one-shot manner, along with 3D scenes, in one stage, at real-time speed (15 FPS) with a low memory footprint (8 GB).

Human3R: Everyone Everywhere All at Once Note: I recorded the video from the interactive demo on their project page (linked in the comment below). Abstract (excerpt): Human3R jointly recovers global multi-person SMPL-X bodies ("everyone"), dense 3D scenes ("everywhere"), and camera trajectories in a single forward pass ("all-at-once"). Our method builds upon the 4D online reconstruction model CUT3R and uses parameter-efficient visual prompt tuning to preserve CUT3R's rich spatiotemporal priors while enabling direct readout of multiple SMPL-X bodies. Human3R is a unified model that eliminates heavy dependencies and iterative refinement. After being trained on the relatively small-scale synthetic dataset BEDLAM for just one day on one GPU, it achieves superior performance with remarkable efficiency: it reconstructs multiple humans in a one-shot manner, along with 3D scenes, in one stage, at real-time speed (15 FPS) with a low memory footprint (8 GB).

MrNeRF

35,832 次观看 • 10 个月前