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。

SuperSplat v2.17.0 is here! ✨ Your free and open source 3D Gaussian Splat Editor. 🗜️ Export to the super-compressed SOG format 🪽 Fly camera controls (WASD) 🎞️ Newly linked tutorial video from Radiance Fields 🪄 UI polish [1 / 2]

Will Eastcott

7,564 subscribers

16,565 次观看 • 6 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

SuperSplat 2.16.0 is here! 🚀 Your free and open source 3D Gaussian Splat Editor 💧 Eyedropper tool 👤 New UI to login and manage your splats [1 / 2]

SuperSplat 2.16.0 is here! 🚀 Your free and open source 3D Gaussian Splat Editor 💧 Eyedropper tool 👤 New UI to login and manage your splats [1 / 2]

Will Eastcott

29,864 次观看 • 7 个月前

SuperSplat 2.15.0 is here! 🚀 Your free and open source 3D Gaussian Splat Editor 📂 Access recent projects via the File menu 🖼️ Updated HTML Viewer export 🌍 Localized into Spanish and Russian [1 / 2]

SuperSplat 2.15.0 is here! 🚀 Your free and open source 3D Gaussian Splat Editor 📂 Access recent projects via the File menu 🖼️ Updated HTML Viewer export 🌍 Localized into Spanish and Russian [1 / 2]

Will Eastcott

11,349 次观看 • 8 个月前

✨SuperSplat 1.8.0 is here✨ Open source 3D Gaussian Splat Editor 🌐HTML 3DGS viewer export 🪄Enhanced rendering of selected splats 🎦Orthographic views 🖼️Save screenshot Links below👇

✨SuperSplat 1.8.0 is here✨ Open source 3D Gaussian Splat Editor 🌐HTML 3DGS viewer export 🪄Enhanced rendering of selected splats 🎦Orthographic views 🖼️Save screenshot Links below👇

Will Eastcott

19,726 次观看 • 1 年前

SuperSplat 2.7.0 is here! 🚀 Your open source editor for 3D Gaussian Splats ✨ This release overhauls the export options for your projects. Now you get fine grained control over spherical harmonics bands, splat selection and more. TRY NOW:

SuperSplat 2.7.0 is here! 🚀 Your open source editor for 3D Gaussian Splats ✨ This release overhauls the export options for your projects. Now you get fine grained control over spherical harmonics bands, splat selection and more. TRY NOW:

Will Eastcott

13,458 次观看 • 1 年前

SuperSplat 2.12.0 is here! 🚀 Your open source 3D Gaussian Splat Editor. ✅ XGRIDS LCC import ✅ Flood fill selection tool ✅ Upgraded HTML Viewer export ✅ Render splats to high quality video ✅ Higher quality rendering in the viewport [1 / 3]

SuperSplat 2.12.0 is here! 🚀 Your open source 3D Gaussian Splat Editor. ✅ XGRIDS LCC import ✅ Flood fill selection tool ✅ Upgraded HTML Viewer export ✅ Render splats to high quality video ✅ Higher quality rendering in the viewport [1 / 3]

Will Eastcott

16,357 次观看 • 9 个月前

Voxel collision in SuperSplat is a game changer. 🧊 It turns any Gaussian splat into accurate 5 cm voxels, automatically. It's super-compressed and far more efficient than a mesh, yet solid enough to climb stairs and walk crossbeams. Free & open source from PlayCanvas 👇

Voxel collision in SuperSplat is a game changer. 🧊 It turns any Gaussian splat into accurate 5 cm voxels, automatically. It's super-compressed and far more efficient than a mesh, yet solid enough to climb stairs and walk crossbeams. Free & open source from PlayCanvas 👇

Will Eastcott

90,562 次观看 • 1 个月前

PlayCanvas Engine v2.13.0 is here 🚀 Your free and open source 3D engine for the web ✅ Streamed LOD system for 3D Gaussian Splats ✅ Splat shader effects framework ✅ Globally sorted splats [1 / 2]

PlayCanvas Engine v2.13.0 is here 🚀 Your free and open source 3D engine for the web ✅ Streamed LOD system for 3D Gaussian Splats ✅ Splat shader effects framework ✅ Globally sorted splats [1 / 2]

PlayCanvas

37,505 次观看 • 8 个月前

The SuperSplat 3DGS Viewer is now Open Source! 🙌 🏃 Tip-top load times and performance 🥽 AR + VR support 🎥 Orbit and fly cameras 🎬 Camera flythrough animations Your 3D Gaussian Splats never looked so good. ✨ Read more:

The SuperSplat 3DGS Viewer is now Open Source! 🙌 🏃 Tip-top load times and performance 🥽 AR + VR support 🎥 Orbit and fly cameras 🎬 Camera flythrough animations Your 3D Gaussian Splats never looked so good. ✨ Read more:

Will Eastcott

31,163 次观看 • 1 年前

Think meshes are the best for e-commerce? Think again. 3D Gaussian Splats are fast and cheap to generate...and with the new SOG format from PlayCanvas, this one is only 5.8MB. 🪄 [1 / 2]

Think meshes are the best for e-commerce? Think again. 3D Gaussian Splats are fast and cheap to generate...and with the new SOG format from PlayCanvas, this one is only 5.8MB. 🪄 [1 / 2]

Will Eastcott

75,123 次观看 • 10 个月前

Introducing powered by Over the Reality. FreeGaussian is a new way to transform your existing photos, videos, and 360 captures for free into high-quality 3D Gaussian splats, directly in your browser. Whether you already have: ↳ a 360 recording captured with any 360 camera ↳ a set of photos ↳ or even a simple video from a place you visited you can now turn it into a photorealistic 3D Gaussian splat. Just go to upload your content, and let the reconstruction happen. Once it’s ready, you can download your 3D Gaussian splat and point cloud, and use them across your own projects, pipelines, or applications.

Introducing powered by Over the Reality. FreeGaussian is a new way to transform your existing photos, videos, and 360 captures for free into high-quality 3D Gaussian splats, directly in your browser. Whether you already have: ↳ a 360 recording captured with any 360 camera ↳ a set of photos ↳ or even a simple video from a place you visited you can now turn it into a photorealistic 3D Gaussian splat. Just go to upload your content, and let the reconstruction happen. Once it’s ready, you can download your 3D Gaussian splat and point cloud, and use them across your own projects, pipelines, or applications.

Over the Reality 🌐

86,245 次观看 • 3 个月前

Here is how you turn a #GaussianSplatting into a walkable world with 2 clicks. First of all, do yourself a favour and try out PostShot. The splat you see was created from a 3-minute video taken with my phone. It ran for around 12 hours on a laptop with a 3060, and the output was beyond my expectations! That being said, whatever tool or app you use to create your Splat, you can import it directly into arrival.space from there you can: - Clean it up and compress it thanks to the direct integration with Supersplat Editor - Generate a rough mesh (that you can export with a paid plan and adjust in Blender ) - Explore it freely on the #web or in #VR Make sure to drop your Space in the comments. Would love to see it!

Here is how you turn a #GaussianSplatting into a walkable world with 2 clicks. First of all, do yourself a favour and try out PostShot. The splat you see was created from a 3-minute video taken with my phone. It ran for around 12 hours on a laptop with a 3060, and the output was beyond my expectations! That being said, whatever tool or app you use to create your Splat, you can import it directly into arrival.space from there you can: - Clean it up and compress it thanks to the direct integration with Supersplat Editor - Generate a rough mesh (that you can export with a paid plan and adjust in Blender ) - Explore it freely on the #web or in #VR Make sure to drop your Space in the comments. Would love to see it!

Gabriele Romagnoli

12,086 次观看 • 1 年前

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.

Here are 10 AI video editor GitHub repos worth bookmarking: 1. Shotcut Most actively maintained open source video editor in 2026. 14K stars. Cross-platform with AI-assisted features. Just shipped a new release April 30, 2026. 2. Kdenlive The closest open source alternative to Adobe Premiere Pro. Multi-track editing, proxy editing, VST audio, and customizable workspace. Best for professional workflows. 3. OpenShot The easiest entry point for beginners. Drag and drop, 400+ transitions, 3D titles, and AI-assisted trimming. 5,700 stars. 4. Blender Not just 3D. Blender's video sequence editor and compositing pipeline is used in professional film production. 18,300 stars. Unmatched for VFX. 5. Recordly Screen recorder with auto-zoom, cursor polish, webcam overlays, and styled frames built in. Built for demo videos and walkthroughs. 6. Wan2.1 Alibaba's open source text-to-video model. Cinema-grade 1080p generation. Apache 2.0. The gold standard for open source video generation in 2026. 7. HunyuanVideo Tencent's 13B parameter open source video model. 11.9K stars. Handles 720p and 1080p with high temporal coherence. 8. CogVideoX Apache 2.0 licensed. Loads natively via Hugging Face Diffusers. Strong prompt following and smooth frame transitions. Needs 16GB VRAM minimum. 12.5K stars. 9. Open-Sora Most starred open source video generation project at 24K stars. Full training pipeline for $200K. Production-level output quality. 10. Mochi 1 Focused entirely on motion quality. The most natural-looking physics of any open source video model. Water, fabric, and human gestures without AI jitter. Apache 2.0.

Kanika

17,726 次观看 • 1 个月前

The wait is over, Guys! 😌 Finally, we've shipped Shadcn Studio 🎉 An open-source registry with copy-and-paste components, blocks, and templates! - Paired with a powerful theme editor to craft, customize, and ship faster. 🚀 - Shadcn Theme Editor & Component variants ✅ - Theme Import/Export ✅ - Save Shadcn Themes ✅ - Shadcn Component Variants ⌛ - Shadcn Figma UI Kit ⌛ - Shadcn Blocks & Templates ⌛ - Figma Plugin, AI, MCP, LLM and more.. ⌛ ➡️ Check it out here: Huge thanks to Anand Patel, Heet Bhalodiya & Aayush Makwana for their incredible work on this! 🙌 Special thanks to shadcn Sahaj 🫱🏼‍🫲🏼 We’d love to hear your thoughts and feedback from the community! Let us know what you think. 😀

The wait is over, Guys! 😌 Finally, we've shipped Shadcn Studio 🎉 An open-source registry with copy-and-paste components, blocks, and templates! - Paired with a powerful theme editor to craft, customize, and ship faster. 🚀 - Shadcn Theme Editor & Component variants ✅ - Theme Import/Export ✅ - Save Shadcn Themes ✅ - Shadcn Component Variants ⌛ - Shadcn Figma UI Kit ⌛ - Shadcn Blocks & Templates ⌛ - Figma Plugin, AI, MCP, LLM and more.. ⌛ ➡️ Check it out here: Huge thanks to Anand Patel, Heet Bhalodiya & Aayush Makwana for their incredible work on this! 🙌 Special thanks to shadcn Sahaj 🫱🏼‍🫲🏼 We’d love to hear your thoughts and feedback from the community! Let us know what you think. 😀

Ajay Patel

85,908 次观看 • 1 年前

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,109 次观看 • 1 年前

1/ 🧠Humans are the best robot data source! 2/ 👓Human egocentric video is rich in quantity, but poor in quality. 3/ Beyond scaling data, smarter representation and architecture matter just as much. 4/ Want an open-source framework to train your own learn-from-human-data robot policy? 🚀We introduce HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Robot-Data-Free ✦ Just 30 min of data per task ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Easy-to-Implement Let's squeeze every bit of signal out of human data! 🌐 Website: 📄 Paper: 💻 Code: 📹 Video: 🧵 1/n

1/ 🧠Humans are the best robot data source! 2/ 👓Human egocentric video is rich in quantity, but poor in quality. 3/ Beyond scaling data, smarter representation and architecture matter just as much. 4/ Want an open-source framework to train your own learn-from-human-data robot policy? 🚀We introduce HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos⬇️ ✦ Zero-Shot Human-to-Robot Transfer ✦ Robot-Data-Free ✦ Just 30 min of data per task ✦ Collect by Anyone, Anytime, Anywhere ✦ Deploy on Any Robot, Any Camera, Any Environment ✦ Open-Source & Easy-to-Implement Let's squeeze every bit of signal out of human data! 🌐 Website: 📄 Paper: 💻 Code: 📹 Video: 🧵 1/n

Zhi (Leo) Wang

109,595 次观看 • 2 个月前

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

Pratham

33,920 次观看 • 6 个月前

3D scanning and rendering is moving so fast - got my splats up and running and I'm mind blown getting ~100fps for this complex 3D scene ⬇️ 🤯 1. WAY faster than NeRF: For comparison, NeRFs would takes around 10 seconds per frame (!) Instead I'm zipping around with FPV controls without breaking a sweat - though I do crash a few times towards the end of the video lol 2. Old Meets New: Gaussian Splatting is cool in that it fuses classical graphics and deep learning techniques. Like NeRFs, this is still a radiance field - just without the slower (ne)ural rendering part. 3. Explicit Representation: Instead you represent a 3D scene as a collection of ellipsoidal "splats" called gaussians. Each gaussian has a position, size, and color. Rendering in real-time is done by projecting into the image plane and alpha blending. 4. Photorealistic Effects: Gaussian splatting use spherical harmonics to represent the view-dependent effects and lighting - allowing surfaces to change color when viewed from different angles, enabling greater photorealism. It doesn't use a neural network, but the training loop is similar to deep learning. 5. Enables Direct Editing: But it's not just speed - with Gaussian Splatting you also get 3D editing support! So you can select, move, and delete stuff, even relight stuff. This type of editing has been more tedious to do with NeRFs and their implicit black box representations. 📲 More tests cooking! Much more to unpack here including simpler explanations. If you enjoyed this post, you might enjoy my feed: Bilawal Sidhu

3D scanning and rendering is moving so fast - got my splats up and running and I'm mind blown getting ~100fps for this complex 3D scene ⬇️ 🤯 1. WAY faster than NeRF: For comparison, NeRFs would takes around 10 seconds per frame (!) Instead I'm zipping around with FPV controls without breaking a sweat - though I do crash a few times towards the end of the video lol 2. Old Meets New: Gaussian Splatting is cool in that it fuses classical graphics and deep learning techniques. Like NeRFs, this is still a radiance field - just without the slower (ne)ural rendering part. 3. Explicit Representation: Instead you represent a 3D scene as a collection of ellipsoidal "splats" called gaussians. Each gaussian has a position, size, and color. Rendering in real-time is done by projecting into the image plane and alpha blending. 4. Photorealistic Effects: Gaussian splatting use spherical harmonics to represent the view-dependent effects and lighting - allowing surfaces to change color when viewed from different angles, enabling greater photorealism. It doesn't use a neural network, but the training loop is similar to deep learning. 5. Enables Direct Editing: But it's not just speed - with Gaussian Splatting you also get 3D editing support! So you can select, move, and delete stuff, even relight stuff. This type of editing has been more tedious to do with NeRFs and their implicit black box representations. 📲 More tests cooking! Much more to unpack here including simpler explanations. If you enjoyed this post, you might enjoy my feed: Bilawal Sidhu

Bilawal Sidhu

337,090 次观看 • 2 年前

GeoLibre v2.1 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. This release adds a QGIS-style Browser panel for exploring data from one place, animated route playback with video export, Wikipedia knowledge cards, and Mapillary street-level images. What's new in v2.1.0 - Browser panel (Data Source Manager): explore and add data from one place. Browse map services, connect to PostGIS databases and drill into their schemas and tables, open local files, and save Favorites, all with full keyboard navigation. - Route animation: send a marker along any line layer, follow the track in 3D with camera controls, and export the whole animation as an MP4 video. - In-browser object detection: run ONNX/YOLO models directly in the webview, with no server or Python required. - Map recording: capture the map canvas, or a drawn bounding box, straight to a video file from the browser. - Native-resolution photo viewer: view geotagged photos at full detail right on the map. - Wikipedia knowledge cards: click any place to pull up its Wikipedia summary and info card. - More planetary basemaps: USGS imagery for nine more celestial bodies, plus a new OpenAerialMap imagery search plugin. Try it out - Live demo: - GitHub: - Documentation: - Release notes: #GIS #Geospatial #OpenSource #RemoteSensing #DataVisualization #MapLibre #GeoLibre

GeoLibre v2.1 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. This release adds a QGIS-style Browser panel for exploring data from one place, animated route playback with video export, Wikipedia knowledge cards, and Mapillary street-level images. What's new in v2.1.0 - Browser panel (Data Source Manager): explore and add data from one place. Browse map services, connect to PostGIS databases and drill into their schemas and tables, open local files, and save Favorites, all with full keyboard navigation. - Route animation: send a marker along any line layer, follow the track in 3D with camera controls, and export the whole animation as an MP4 video. - In-browser object detection: run ONNX/YOLO models directly in the webview, with no server or Python required. - Map recording: capture the map canvas, or a drawn bounding box, straight to a video file from the browser. - Native-resolution photo viewer: view geotagged photos at full detail right on the map. - Wikipedia knowledge cards: click any place to pull up its Wikipedia summary and info card. - More planetary basemaps: USGS imagery for nine more celestial bodies, plus a new OpenAerialMap imagery search plugin. Try it out - Live demo: - GitHub: - Documentation: - Release notes: #GIS #Geospatial #OpenSource #RemoteSensing #DataVisualization #MapLibre #GeoLibre

Qiusheng Wu

11,627 次观看 • 14 天前

[SIGGRAPH 2025] Photoreal Scene Reconstruction from an Egocentric Device Contributions: 1. We address the importance of employing visual-inertial bundle adjustment (VIBA) that accounts for the rolling-shutter behavior of the RGB camera. This provides a continuous camera trajectory to model pixel movement in neural reconstruction. Our experiments demonstrate that using VIBA consistently improves the novel view quality in Gaussian Splatting by +1 dB in PSNR. 2. We introduce a rasterization-based image formulation pipeline that addresses common artifacts in physical image formation, including rolling shutter, lens shading, exposure, and gain compensation. Our approach is distinct in that we represent image poses as posed pixel arrays sampled from a continuous trajectory, rather than assigning a single camera pose per image, and preserve the merit of Gaussian rasterization. Unlike existing methods that require ray-tracing Gaussians, e.g., [Moenne-Loccoz et al. 2024], our formulation is applicable to general-purpose rasterization-based Gaussian splatting. When applied to 3D Gaussian Splatting (3DGS) [Kerbl et al. 2023], our approach can further enhance reconstruction quality by +1 dB. We outperform existing baselines and demonstrate a substantial quality improvement in handling complex scenes observed by egocentric devices. 3. To reduce the effect of blur from rapid head motion in darker indoor scenes, we propose a strategy of deliberately underexposing input videos during capture, inspired by HDR+ [Hasinoff et al. 2016]. We demonstrate that we can reconstruct high-quality, noise-free scene radiance from noisy, dim input videos, and further render sharp, blur-free videos at a higher dynamic range.

[SIGGRAPH 2025] Photoreal Scene Reconstruction from an Egocentric Device Contributions: 1. We address the importance of employing visual-inertial bundle adjustment (VIBA) that accounts for the rolling-shutter behavior of the RGB camera. This provides a continuous camera trajectory to model pixel movement in neural reconstruction. Our experiments demonstrate that using VIBA consistently improves the novel view quality in Gaussian Splatting by +1 dB in PSNR. 2. We introduce a rasterization-based image formulation pipeline that addresses common artifacts in physical image formation, including rolling shutter, lens shading, exposure, and gain compensation. Our approach is distinct in that we represent image poses as posed pixel arrays sampled from a continuous trajectory, rather than assigning a single camera pose per image, and preserve the merit of Gaussian rasterization. Unlike existing methods that require ray-tracing Gaussians, e.g., [Moenne-Loccoz et al. 2024], our formulation is applicable to general-purpose rasterization-based Gaussian splatting. When applied to 3D Gaussian Splatting (3DGS) [Kerbl et al. 2023], our approach can further enhance reconstruction quality by +1 dB. We outperform existing baselines and demonstrate a substantial quality improvement in handling complex scenes observed by egocentric devices. 3. To reduce the effect of blur from rapid head motion in darker indoor scenes, we propose a strategy of deliberately underexposing input videos during capture, inspired by HDR+ [Hasinoff et al. 2016]. We demonstrate that we can reconstruct high-quality, noise-free scene radiance from noisy, dim input videos, and further render sharp, blur-free videos at a higher dynamic range.

MrNeRF

15,244 次观看 • 1 年前

💫 The Ultimate AI Video Agent is here — Welcome to Flova! Create cinematic, movie-quality videos from story to final cut — all powered by AI. With Flova, you can script, storyboard, generate characters, direct camera angles, add music, and export — all in one platform. Beta perks: claim 500 free credits every week, invite friends to earn 300 credits each. Subscribers enjoy 10 referral codes, limited free images, and buy 1 → 2.5 credits! Step into the AI-powered creative universe and turn your imagination into professional videos today. #FlovaAI #AIVideoAgent #Storytelling #AIForCreators #DigitalCreativity #AIAnimation #CreativeAI #Sora2 #NanoBananaPro #Veo3 #Gemini

💫 The Ultimate AI Video Agent is here — Welcome to Flova! Create cinematic, movie-quality videos from story to final cut — all powered by AI. With Flova, you can script, storyboard, generate characters, direct camera angles, add music, and export — all in one platform. Beta perks: claim 500 free credits every week, invite friends to earn 300 credits each. Subscribers enjoy 10 referral codes, limited free images, and buy 1 → 2.5 credits! Step into the AI-powered creative universe and turn your imagination into professional videos today. #FlovaAI #AIVideoAgent #Storytelling #AIForCreators #DigitalCreativity #AIAnimation #CreativeAI #Sora2 #NanoBananaPro #Veo3 #Gemini

FlovaAI Japan

161,296 次观看 • 7 个月前