Loading video...

Video Failed to Load

Go Home

How do we reconstruct a 3D scene from photos with varying exposures? Standard methods often fail, leaving you with blown-out colors or disturbing shadows. We're excited to introduce Neural Exposure Fields (NExF), our new work accepted at #NeurIPS2025! 🧵

Mi_Niemeyer's profile picture

Michael Niemeyer

3,635 subscribers

132,076 views • 9 months ago •via X (Twitter)

EducationScience & Technology#NeurIPS2025
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

📢📢📢 Excited to share our ICLR25 work, ArtGS, which can reconstruct articulated objects and scenes from human-scene interactions. 💻🖱️🧱🪑📖 Understanding physics and articulation is extremely important. With ArtGS, we can build a digital and simulatable replica of the real 3D world with minimal human effort!
0:38

📢📢📢 Excited to share our ICLR25 work, ArtGS, which can reconstruct articulated objects and scenes from human-scene interactions. 💻🖱️🧱🪑📖 Understanding physics and articulation is extremely important. With ArtGS, we can build a digital and simulatable replica of the real 3D world with minimal human effort!

Siyuan Huang

12,819 views • 1 year ago

SpecNeRF: Gaussian Directional Encoding for Specular Reflections paper page: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.
3:41

SpecNeRF: Gaussian Directional Encoding for Specular Reflections paper page: Neural radiance fields have achieved remarkable performance in modeling the appearance of 3D scenes. However, existing approaches still struggle with the view-dependent appearance of glossy surfaces, especially under complex lighting of indoor environments. Unlike existing methods, which typically assume distant lighting like an environment map, we propose a learnable Gaussian directional encoding to better model the view-dependent effects under near-field lighting conditions. Importantly, our new directional encoding captures the spatially-varying nature of near-field lighting and emulates the behavior of prefiltered environment maps. As a result, it enables the efficient evaluation of preconvolved specular color at any 3D location with varying roughness coefficients. We further introduce a data-driven geometry prior that helps alleviate the shape radiance ambiguity in reflection modeling. We show that our Gaussian directional encoding and geometry prior significantly improve the modeling of challenging specular reflections in neural radiance fields, which helps decompose appearance into more physically meaningful components.

AK

33,933 views • 2 years ago

We're excited to work together with Microsoft to create a truly innovative, secure and seamless user experience. We’ve been blown away by the response to Manus from users around the world. By partnering with Azure AI Foundry, we look forward to delighting even more users globally. Check out our video shown at Microsoft Build – and join us on this journey!
1:09

We're excited to work together with Microsoft to create a truly innovative, secure and seamless user experience. We’ve been blown away by the response to Manus from users around the world. By partnering with Azure AI Foundry, we look forward to delighting even more users globally. Check out our video shown at Microsoft Build – and join us on this journey!

Manus

191,645 views • 1 year ago

Yesterday, we launched our API. Today, we introduce a redesigned platform interface to go with it. Watching Posthog sessions is a painful necessity. Seeing users sign up, click around, get confused, and leave has been a flow we’ve seen all too often. With Mosaic, we set out to redesign the video editing interface from first principles. But conveying what a new interface does & doesn’t do intuitively isn’t so easy. That’s why today, we introduce a redesigned platform interface that changes a user’s experience completely. From when you first sign in to how you navigate our documentation — everything has been rethought. Some of my favorite new features: > Cmd + K to Navigate & Search from anywhere > More Editing Workflow Templates > More Motion Graphics Styles / Templates > More Canvas Presets & Usability Improvements > Automations / API > Organizations & Workspaces > Revamped Pricing page Check it out out edit .mosaic .so and let me know where you think product friction still exists. I’ll be watching on Posthog ;) More on all the new features below 🧵
1:19

Yesterday, we launched our API. Today, we introduce a redesigned platform interface to go with it. Watching Posthog sessions is a painful necessity. Seeing users sign up, click around, get confused, and leave has been a flow we’ve seen all too often. With Mosaic, we set out to redesign the video editing interface from first principles. But conveying what a new interface does & doesn’t do intuitively isn’t so easy. That’s why today, we introduce a redesigned platform interface that changes a user’s experience completely. From when you first sign in to how you navigate our documentation — everything has been rethought. Some of my favorite new features: > Cmd + K to Navigate & Search from anywhere > More Editing Workflow Templates > More Motion Graphics Styles / Templates > More Canvas Presets & Usability Improvements > Automations / API > Organizations & Workspaces > Revamped Pricing page Check it out out edit .mosaic .so and let me know where you think product friction still exists. I’ll be watching on Posthog ;) More on all the new features below 🧵

Adish Jain ☕️

61,731 views • 4 months ago

🚨MAJOR BREAKING: Rep. Robert Garcia and Oversight Democrats have just released a SECOND BATCH of 150+ photos and videos from Epstein Island. Earlier, Dems put out images including a disturbing dentist chair with masks on the walls. Garcia dropped the hammer: “Our job is to put out what we receive… “I wish that Republicans would do the same thing.” You can see these new photos and videos below. 👇
0:30

🚨MAJOR BREAKING: Rep. Robert Garcia and Oversight Democrats have just released a SECOND BATCH of 150+ photos and videos from Epstein Island. Earlier, Dems put out images including a disturbing dentist chair with masks on the walls. Garcia dropped the hammer: “Our job is to put out what we receive… “I wish that Republicans would do the same thing.” You can see these new photos and videos below. 👇

CALL TO ACTIVISM

119,831 views • 8 months ago

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.
0:42

Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields paper page: Editing a local region or a specific object in a 3D scene represented by a NeRF is challenging, mainly due to the implicit nature of the scene representation. Consistently blending a new realistic object into the scene adds an additional level of difficulty. We present Blended-NeRF, a robust and flexible framework for editing a specific region of interest in an existing NeRF scene, based on text prompts or image patches, along with a 3D ROI box. Our method leverages a pretrained language-image model to steer the synthesis towards a user-provided text prompt or image patch, along with a 3D MLP model initialized on an existing NeRF scene to generate the object and blend it into a specified region in the original scene. We allow local editing by localizing a 3D ROI box in the input scene, and seamlessly blend the content synthesized inside the ROI with the existing scene using a novel volumetric blending technique. To obtain natural looking and view-consistent results, we leverage existing and new geometric priors and 3D augmentations for improving the visual fidelity of the final result. We test our framework both qualitatively and quantitatively on a variety of real 3D scenes and text prompts, demonstrating realistic multi-view consistent results with much flexibility and diversity compared to the baselines. Finally, we show the applicability of our framework for several 3D editing applications, including adding new objects to a scene, removing/replacing/altering existing objects, and texture conversion.

AK

62,768 views • 3 years ago

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be used to reconstruct photorealistic scenes, and introduce a corresponding differentiable CUDA rasterizer that enables real-time rendering. On real-world scenes, LinPrim achieves comparable image quality with fewer primitives, adding a practical polyhedral option to the 3D scene representation toolbox and expanding the known design space. 🌍 🎥 Amazing work by Nicolas von Lützow!
0:35

📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be used to reconstruct photorealistic scenes, and introduce a corresponding differentiable CUDA rasterizer that enables real-time rendering. On real-world scenes, LinPrim achieves comparable image quality with fewer primitives, adding a practical polyhedral option to the 3D scene representation toolbox and expanding the known design space. 🌍 🎥 Amazing work by Nicolas von Lützow!

Matthias Niessner

11,413 views • 1 year ago

We're celebrating 30 years of PlayStation in Australia with a trip down memory lane and an epic 30th Anniversary PS5 Console to give away! All you have to do is share your favourite PlayStation memory. Is it opening your first PlayStation? A scene that's stuck with you? Or the people you've met? 💙 HOW TO ENTER: You can post in the comments below or submit your entry using the hashtag #PlayStationAU30Memories. Text under 30 words, photos and videos accepted. Entries may be included in our 30th Anniversary celebration content. Good luck, legends!
0:42

We're celebrating 30 years of PlayStation in Australia with a trip down memory lane and an epic 30th Anniversary PS5 Console to give away! All you have to do is share your favourite PlayStation memory. Is it opening your first PlayStation? A scene that's stuck with you? Or the people you've met? 💙 HOW TO ENTER: You can post in the comments below or submit your entry using the hashtag #PlayStationAU30Memories. Text under 30 words, photos and videos accepted. Entries may be included in our 30th Anniversary celebration content. Good luck, legends!

PlayStation AU

10,208 views • 9 months ago

Design agencies are evolving. Our goal with Off/Menu™ has always been to lead, not follow. To grow from 7 to 8-figures, things have to change. We're rethinking everything. - Business model. - Team. - How we work. - Storytelling. We're working on something new. In the meantime, here's a fun, temporary site. We hope you like it.
0:25

Design agencies are evolving. Our goal with Off/Menu™ has always been to lead, not follow. To grow from 7 to 8-figures, things have to change. We're rethinking everything. - Business model. - Team. - How we work. - Storytelling. We're working on something new. In the meantime, here's a fun, temporary site. We hope you like it.

Hunter Hammonds

25,691 views • 1 year ago

We just cracked document editing without drawing boxes. We’re excited to launch Edit – a new endpoint that fills out any document automatically. Edit revolutionizes document automation by automatically finding all blank fields, tables, and checkboxes in forms, then intelligently filling them with your data. To try it, sign up for the waitlist at or see it in action down below 🧵
1:33

We just cracked document editing without drawing boxes. We’re excited to launch Edit – a new endpoint that fills out any document automatically. Edit revolutionizes document automation by automatically finding all blank fields, tables, and checkboxes in forms, then intelligently filling them with your data. To try it, sign up for the waitlist at or see it in action down below 🧵

Reducto

260,110 views • 1 year ago

After reading community feedback on Luminous Dream's previous teaser, we're confident enough to show you our third teaser! This teaser showcases how we went back to using similar values from v1.0 for shadows, and overall lighting have received minor tweaks. The tonemapper in the pack is changing from "hable" to "aces". With that, we also introduced per-biome configs, which means some biomes will have warmer/cooler tones. I'd like to add that we're not going to add dark shadows, because of how VV auto-exposure works, dark shadows look odd. If this is received well, the changes seen in this teaser will remain until launch, with a few minor adjustments of course! Let us know what you think! <3
0:30

After reading community feedback on Luminous Dream's previous teaser, we're confident enough to show you our third teaser! This teaser showcases how we went back to using similar values from v1.0 for shadows, and overall lighting have received minor tweaks. The tonemapper in the pack is changing from "hable" to "aces". With that, we also introduced per-biome configs, which means some biomes will have warmer/cooler tones. I'd like to add that we're not going to add dark shadows, because of how VV auto-exposure works, dark shadows look odd. If this is received well, the changes seen in this teaser will remain until launch, with a few minor adjustments of course! Let us know what you think! <3

FoxyStar Studios

14,794 views • 3 months ago

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives paper page: Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made of a small set of textured primitives. Such representations are interpretable, easy to manipulate and suited for physics-based simulations. Moreover, unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images through differentiable rendering. Specifically, we model primitives as textured superquadric meshes and optimize their parameters from scratch with an image rendering loss. We highlight the importance of modeling transparency for each primitive, which is critical for optimization and also enables handling varying numbers of primitives. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points, while providing amodal shape completions of unseen object regions. We compare our approach to the state of the art on diverse scenes from DTU, and demonstrate its robustness on real-life captures from BlendedMVS and Nerfstudio. We also showcase how our results can be used to effortlessly edit a scene or perform physical simulations.
0:27

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives paper page: Given a set of calibrated images of a scene, we present an approach that produces a simple, compact, and actionable 3D world representation by means of 3D primitives. While many approaches focus on recovering high-fidelity 3D scenes, we focus on parsing a scene into mid-level 3D representations made of a small set of textured primitives. Such representations are interpretable, easy to manipulate and suited for physics-based simulations. Moreover, unlike existing primitive decomposition methods that rely on 3D input data, our approach operates directly on images through differentiable rendering. Specifically, we model primitives as textured superquadric meshes and optimize their parameters from scratch with an image rendering loss. We highlight the importance of modeling transparency for each primitive, which is critical for optimization and also enables handling varying numbers of primitives. We show that the resulting textured primitives faithfully reconstruct the input images and accurately model the visible 3D points, while providing amodal shape completions of unseen object regions. We compare our approach to the state of the art on diverse scenes from DTU, and demonstrate its robustness on real-life captures from BlendedMVS and Nerfstudio. We also showcase how our results can be used to effortlessly edit a scene or perform physical simulations.

AK

38,571 views • 3 years ago

🧸yeah...2.0 is where BTS is at right now after going through all the change and growth. It feels like we have stepped into a new chapter and reached another level. Like how we say "you know how we do" in the song. 🧸We're a lot more confident in our (?) now. With this track, we wanted to show who we are today and the way we're moving forward with stronger conviction.
0:32

🧸yeah...2.0 is where BTS is at right now after going through all the change and growth. It feels like we have stepped into a new chapter and reached another level. Like how we say "you know how we do" in the song. 🧸We're a lot more confident in our (?) now. With this track, we wanted to show who we are today and the way we're moving forward with stronger conviction.

ً

12,791 views • 4 months ago

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai
0:25

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

Matthias Niessner

19,004 views • 4 months ago

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein
0:30

📢📢 𝐏𝐞𝐫𝐜𝐇𝐞𝐚𝐝: 𝐏𝐞𝐫𝐜𝐞𝐩𝐭𝐮𝐚𝐥 𝐇𝐞𝐚𝐝 𝐌𝐨𝐝𝐞𝐥 𝐟𝐨𝐫 𝐒𝐢𝐧𝐠𝐥𝐞-𝐈𝐦𝐚𝐠𝐞 𝟑𝐃 𝐇𝐞𝐚𝐝 𝐑𝐞𝐜𝐨𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧 & 𝐄𝐝𝐢𝐭𝐢𝐧𝐠📢📢 PercHead reconstructs realistic 3D heads from a single image and enables disentangled 3D editing via geometric controls and style inputs from images or text. At its core is a generalized 3D head decoder trained with perceptual supervision from DINOv2 and SAM 2.1. We find that our new perceptual loss formulation improves reconstruction fidelity compared to commonly-used methods such as LPIPS. Our trained reconstruction model is able to generate 3D-consistent heads from a single input image. Even with challenging side-view inputs, the model robustly infers missing regions for a coherent, high-fidelity output. In addition, our architecture seamlessly adapts to downstream tasks: by swapping the encoder, we can transform the model into a disentangled 3D editing pipeline. In this scenario, we can control geometry through - potentially hand-drawn - segmentation maps, and condition style via image or text prompt. We also provide an interactive GUI to enable the exploration of our editing pipeline. 🌍 📽️ Great work by Antonio Oroz and Tobias Kirschstein

Matthias Niessner

18,855 views • 8 months ago

Drivable 3D Gaussian Avatars paper page: present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during training, dense input images during testing, or both. The ones based on neural radiance fields also tend to be prohibitively slow for telepresence applications. This work uses the recently presented 3D Gaussian Splatting (3DGS) technique to render realistic humans at real-time framerates, using dense calibrated multi-view videos as input. To deform those primitives, we depart from the commonly used point deformation method of linear blend skinning (LBS) and use a classic volumetric deformation method: cage deformations. Given their smaller size, we drive these deformations with joint angles and keypoints, which are more suitable for communication applications. Our experiments on nine subjects with varied body shapes, clothes, and motions obtain higher-quality results than state-of-the-art methods when using the same training and test data.
6:20

Drivable 3D Gaussian Avatars paper page: present Drivable 3D Gaussian Avatars (D3GA), the first 3D controllable model for human bodies rendered with Gaussian splats. Current photorealistic drivable avatars require either accurate 3D registrations during training, dense input images during testing, or both. The ones based on neural radiance fields also tend to be prohibitively slow for telepresence applications. This work uses the recently presented 3D Gaussian Splatting (3DGS) technique to render realistic humans at real-time framerates, using dense calibrated multi-view videos as input. To deform those primitives, we depart from the commonly used point deformation method of linear blend skinning (LBS) and use a classic volumetric deformation method: cage deformations. Given their smaller size, we drive these deformations with joint angles and keypoints, which are more suitable for communication applications. Our experiments on nine subjects with varied body shapes, clothes, and motions obtain higher-quality results than state-of-the-art methods when using the same training and test data.

AK

327,105 views • 2 years ago

Today we're excited to announce our public launch on Base 🔵, following a successful private testing phase, two security audits, and a white hat competition. At Velvet Capital, we streamline onchain portfolio management and social trading with our Intent Operating System for DeFi: - Trade any token via our smart execution engine - Access top DeFi protocols - Explore other people's portfolios We combine best-in-class trade execution with a DeFi social layer! Check it out below & keep reading to learn more about what you can do with the new app on Base
0:23

Today we're excited to announce our public launch on Base 🔵, following a successful private testing phase, two security audits, and a white hat competition. At Velvet Capital, we streamline onchain portfolio management and social trading with our Intent Operating System for DeFi: - Trade any token via our smart execution engine - Access top DeFi protocols - Explore other people's portfolios We combine best-in-class trade execution with a DeFi social layer! Check it out below & keep reading to learn more about what you can do with the new app on Base

Velvet | SocialFAI

131,222 views • 2 years ago

Drop the camera, and bang -- the robots do the job without camera calibration or additional data collection. We want robots to manipulate anywhere! Our new work, **Maniwhere**, enables robots to manipulate objects from any camera view with any background. Isn't this the generalization every roboticist is looking for? How do we achieve this with sim2real? You can check this thread from Zhecheng Yuan ! And the website is here:
0:29

Drop the camera, and bang -- the robots do the job without camera calibration or additional data collection. We want robots to manipulate anywhere! Our new work, **Maniwhere**, enables robots to manipulate objects from any camera view with any background. Isn't this the generalization every roboticist is looking for? How do we achieve this with sim2real? You can check this thread from Zhecheng Yuan ! And the website is here:

Huazhe Harry Xu

27,564 views • 2 years ago

RFK’s VP Nicole Shanahan says they are debating whether to stay in the race or drop out and join forces with Trump: “There’s two options that we're looking at and one is staying in, forming that new party, but we run the risk of a Kamala Harris and Waltz presidency because we draw more votes from Trump. Or we walk away right now and join forces with with Donald Trump and explain to our base why we're making this decision.”
2:09

RFK’s VP Nicole Shanahan says they are debating whether to stay in the race or drop out and join forces with Trump: “There’s two options that we're looking at and one is staying in, forming that new party, but we run the risk of a Kamala Harris and Waltz presidency because we draw more votes from Trump. Or we walk away right now and join forces with with Donald Trump and explain to our base why we're making this decision.”

End Tribalism in Politics

4,054,163 views • 1 year ago

Welcome to the 3D Layer of the Internet We are thrilled to share our latest features Prompt-to-3D engine and Scene Studio Your text based prompts and photos can now be transformed from simple concepts into fully-rendered, interactive 3D models. It parses complex topology, handles multi-view reconstruction, and even lets you restyle your model instantly with single-click filters like low-poly, voxel, and Voronoi shells. Within the all-new Scene Studio, you can construct immersive 3D environments that reflect your exact style. Position your assets in a full sandbox space, adjust advanced lighting and environment colors, and add the finishing touches with custom camera angles, fog settings, and real-time script parameters. This is the future of the open web. This is
3:00

Welcome to the 3D Layer of the Internet We are thrilled to share our latest features Prompt-to-3D engine and Scene Studio Your text based prompts and photos can now be transformed from simple concepts into fully-rendered, interactive 3D models. It parses complex topology, handles multi-view reconstruction, and even lets you restyle your model instantly with single-click filters like low-poly, voxel, and Voronoi shells. Within the all-new Scene Studio, you can construct immersive 3D environments that reflect your exact style. Position your assets in a full sandbox space, adjust advanced lighting and environment colors, and add the finishing touches with custom camera angles, fog settings, and real-time script parameters. This is the future of the open web. This is

three.ws

37,254 views • 1 month ago