Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Mind blown by this new CVPR 2026 paper: tttLRM🤯 It introduces a Test-Time Training layer for long-context autoregressive 3D reconstruction with linear complexity. Multiple image observations are compressed into fast weights that keep updating during inference, forming an implicit scene representation that can be decoded into explicit formats such...

KIRI_Engine_App's profile picture

KIRI Engine - 3D Scanner App

5,588 subscribers

16,949 Aufrufe • vor 6 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Spatial reconstruction is a long-context problem: real scenes come with hundreds of images. But O(N²) transformer-based models don’t scale efficiently. Introducing: 🤐ZipMap (CVPR ’26): Linear-Time, Stateful 3D Reconstruction via Test-Time Training (TTT). ZipMap “zips” a large image collection into an implicit TTT scene state in a single linear-time operation. The state will then be decoded into spatial outputs, and can be queried efficiently for novel-view geometry and appearance (~100 FPS) ZipMap is not only much faster (>20× faster than VGGT), but also matches or surpasses the accuracy of all SOTA models.
0:35

Spatial reconstruction is a long-context problem: real scenes come with hundreds of images. But O(N²) transformer-based models don’t scale efficiently. Introducing: 🤐ZipMap (CVPR ’26): Linear-Time, Stateful 3D Reconstruction via Test-Time Training (TTT). ZipMap “zips” a large image collection into an implicit TTT scene state in a single linear-time operation. The state will then be decoded into spatial outputs, and can be queried efficiently for novel-view geometry and appearance (~100 FPS) ZipMap is not only much faster (>20× faster than VGGT), but also matches or surpasses the accuracy of all SOTA models.

Haian Jin

79,916 Aufrufe • vor 6 Monaten

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:
0:50

📢 Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation Got only one or a few images and wondering if recovering the 3D environment is a reconstruction or generation problem? Why not do it with a generative reconstruction model! We show that a camera-conditioned video diffusion model can be transformed into a generative reconstruction model that directly outputs a high-quality 3D Gaussian Splatting representation through self-distillation, without requiring real-world training data. Check out our results in the video (wait for dynamic scenes in the second half!) : Project Page: Code and Models: Paper:

Sherwin Bahmani

66,869 Aufrufe • vor 1 Jahr

Scaling 3D scene data is a long-standing challenge in scene understanding, spatial reasoning, and robotics. Since scanning, reconstruction, and labeling are so labor-intensive, data scarcity has remained a major bottleneck. 🛑 To solve this, we propose SceneVerse++: Lifting Unlabeled Internet-level Data for 3D Scene Understanding (CVPR 2026). By reconstructing internet videos and annotating 3D scenes automatically, we’ve created a massive real-world dataset for end-to-end understanding. 🌐📐 SceneVerse++ makes it easy to scale "in-the-wild" 3D scenes toward more capable spatial reasoning systems. This significantly promotes progress in 3D VQA, visual navigation, and broader tasks in Embodied AI and Robotics. 🤖🦾 We are fully open-sourced! Check out the paper, code, and data here: 🌐 Project: 📄 Paper: 📊 Dataset: Code:
2:13

Scaling 3D scene data is a long-standing challenge in scene understanding, spatial reasoning, and robotics. Since scanning, reconstruction, and labeling are so labor-intensive, data scarcity has remained a major bottleneck. 🛑 To solve this, we propose SceneVerse++: Lifting Unlabeled Internet-level Data for 3D Scene Understanding (CVPR 2026). By reconstructing internet videos and annotating 3D scenes automatically, we’ve created a massive real-world dataset for end-to-end understanding. 🌐📐 SceneVerse++ makes it easy to scale "in-the-wild" 3D scenes toward more capable spatial reasoning systems. This significantly promotes progress in 3D VQA, visual navigation, and broader tasks in Embodied AI and Robotics. 🤖🦾 We are fully open-sourced! Check out the paper, code, and data here: 🌐 Project: 📄 Paper: 📊 Dataset: Code:

Siyuan Huang

12,842 Aufrufe • vor 5 Monaten

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi
1:00

🍺 LagerNVS (CVPR 2026) 🍺 LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which - performs rendering in real time, - generalizes to in-the-wild data, - works with and without known source cameras, - sets a new state-of-the-art among deterministic methods, - can be paired with a diffusion decoder for generative extrapolation. LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training: (1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering. (2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware. Both substantially improve performance. Project page: Code: Paper: Models: Work done with Jianyuan Minghao Chen Christian Rupprecht and Andrea Vedaldi

Stan Szymanowicz

32,815 Aufrufe • vor 6 Monaten

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting
0:38

Adobe.. has released a tool that combines Generative Gaussian Splats with a Diffusion layer and it's not all over the internet? WHAT IS GOING ON :D I had to test this out ofc! Substance 3D viewer, the new 3d viewer just released by Adobe, not only supports viewing of a large, large list of 3d formats, but it also supports generating of 3d models as Gaussian Splats. Combine that with the built-in 3d to image functionality and you basically have at least a few of the steps I've been doing for the last year or so using multiple tools. Exciting stuff! The new Photoshop Beta also supports the 3D viewer and you can import 3d files directly in photoshop as smart objects linked to the viewer. The elements you prompt in based on your models, can be easily exported to your clipboard without backgrounds making it very easy to use this in your normal image editing workflows. I have a suspicion that we'll see much more of this in other Adobe tools and I'm very curious to see this used for things like this in more 3d tools than "just" Adobe Neo (which is fantastic btw). #adobe #art #gaussiansplatting

Martin Nebelong

280,121 Aufrufe • vor 1 Jahr

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.
2:42

Another city. Another full 3D Gaussian Splat reconstruction. This entire neighborhood was captured while walking with an Insta360 X5, then processed with our GPU pipeline and transformed into a high-fidelity, machine-readable 3D environment with Over the Reality. What you’re seeing is not an isolated virtual world. It’s a 3D digital twin of a real-world location, built from structured spatial data where every building, street, and detail can become usable by AI, robotics, and XR. And it’s happening at scale, across cities in more than 180 countries every day. Have an Insta360 X5 and want to become a mapper? Apply here: Want to build a 3D Gaussian Splat from a video you already recorded? Do it for free at powered by Over the Reality.

Over the Reality 🌐

400,282 Aufrufe • vor 5 Monaten

Super excited for #ECCV'26 in Malmö! Our group will present a series of cutting-edge works, including two orals and a spotlight, around generative AI that cover 3D scene generation, photo-realistic avatars, agentic modeling, and much more! I'll also give several workshop talks about our recent research, including a few exciting updates what we're cooking at SpAItial AI :) 1. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation *(oral)* 2. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields *(oral)* 3. Face Anything: 4D Face Reconstruction from Any Image Sequence *(spotlight)* 4. Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image 5. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow 6. DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing 7. WorldAgents: Can Foundation Image Models be Agents for 3D World Models? 8. World Reconstruction From Inconsistent Views 9. Head Avatars with Dynamic Explicit Hair Great work by Nicolas von Lützow Haoxuan Li Ziya Erkoç Umut Kocasarı Vanessa Sklyarova Lukas Höllein Quan Meng Jinxin Ai Simon Giebenhain and all amazing collaborators!
0:27

Super excited for #ECCV'26 in Malmö! Our group will present a series of cutting-edge works, including two orals and a spotlight, around generative AI that cover 3D scene generation, photo-realistic avatars, agentic modeling, and much more! I'll also give several workshop talks about our recent research, including a few exciting updates what we're cooking at SpAItial AI :) 1. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation *(oral)* 2. TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields *(oral)* 3. Face Anything: 4D Face Reconstruction from Any Image Sequence *(spotlight)* 4. Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image 5. Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow 6. DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing 7. WorldAgents: Can Foundation Image Models be Agents for 3D World Models? 8. World Reconstruction From Inconsistent Views 9. Head Avatars with Dynamic Explicit Hair Great work by Nicolas von Lützow Haoxuan Li Ziya Erkoç Umut Kocasarı Vanessa Sklyarova Lukas Höllein Quan Meng Jinxin Ai Simon Giebenhain and all amazing collaborators!

Matthias Niessner

14,897 Aufrufe • vor 22 Tagen

📢 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

11,425 Aufrufe • vor 1 Jahr

Nvidia announces GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning paper page: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.
5:36

Nvidia announces GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning paper page: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.

AK

141,058 Aufrufe • vor 2 Jahren

America. Europe. Africa. Asia. Oceania. More than 250,000 real-world locations across 120+ countries have already been transformed into ultra high quality 3D Gaussian Splats by Over the Reality. From city centers and museums to beaches, mountains, and historical landmarks, every mapping created by our community contributes to a growing machine-readable representation of the physical world. This scene started as a simple Insta360 X5 recording and was transformed into a digital twin, where geometry, textures, and spatial structure are preserved and can be used by AI, Robotics, VPS, XR, and next-generation world models. This is what city-scale 3D mapping looks like. The link to become an Insta360 X5 mapper is in the first comment. 👇
1:22

America. Europe. Africa. Asia. Oceania. More than 250,000 real-world locations across 120+ countries have already been transformed into ultra high quality 3D Gaussian Splats by Over the Reality. From city centers and museums to beaches, mountains, and historical landmarks, every mapping created by our community contributes to a growing machine-readable representation of the physical world. This scene started as a simple Insta360 X5 recording and was transformed into a digital twin, where geometry, textures, and spatial structure are preserved and can be used by AI, Robotics, VPS, XR, and next-generation world models. This is what city-scale 3D mapping looks like. The link to become an Insta360 X5 mapper is in the first comment. 👇

Over the Reality 🌐

19,398 Aufrufe • vor 3 Monaten

The Genie 3 release is a perfect moment to have a discussion about the future of 3D But first it would be nice to make the terminology more clear, specifically: What is a “spatial representation” Implicit vs Explicit Generalization vs Specialization Reconstruction vs Generation Production vs Execution Let’s start: For me, a spatial representation is just a way to describe a thing in the physical world The core property that makes it useful is consistency You can enforce consistency explicitly via rendering equations, geometric constraints, and physics Or implicitly, purely through training data Then, your representation parameters can be explicit, like points, gaussians, triangles, voxels, etc. Or implicit, weights or latent vectors Parameters alone are not the representation. It’s a combination of the parameters, the process that produces them, and the way you materialize them through a function (physics-based rendering, simulation, neural network, etc.) Generalization means you take data from multiple scene observations, and then produce a map from desired input to representation parameters Specialization means you take single-scene observations and directly fit a function parameters to describe thar scene Many representations can serve both of the approaches, as long as you keep them differentiable Both of the above can be used for reconstruction, where the main goal is to explain observations through a lens of physics (hard constraint) On the other hand, generation needs generalization, and its task is to produce statistically plausible results that could be conditioned on observations (soft constraint) Both tasks are not solved yet and they can complement each other in various ways Yet another important aspect is the difference between production and execution Production = process of going from inputs to parameters Execution = process of going from parameters to result It’s important to separate these, because most usecases require fast execution to be viable which is severely constrained by the hardware So, are *world models* like Genie an important step forward? Yes Do they make other representations obsolete? Maybe some of them - but there are tons of economically valuable tasks that won’t be solved by it, at least in any observable future
0:33

The Genie 3 release is a perfect moment to have a discussion about the future of 3D But first it would be nice to make the terminology more clear, specifically: What is a “spatial representation” Implicit vs Explicit Generalization vs Specialization Reconstruction vs Generation Production vs Execution Let’s start: For me, a spatial representation is just a way to describe a thing in the physical world The core property that makes it useful is consistency You can enforce consistency explicitly via rendering equations, geometric constraints, and physics Or implicitly, purely through training data Then, your representation parameters can be explicit, like points, gaussians, triangles, voxels, etc. Or implicit, weights or latent vectors Parameters alone are not the representation. It’s a combination of the parameters, the process that produces them, and the way you materialize them through a function (physics-based rendering, simulation, neural network, etc.) Generalization means you take data from multiple scene observations, and then produce a map from desired input to representation parameters Specialization means you take single-scene observations and directly fit a function parameters to describe thar scene Many representations can serve both of the approaches, as long as you keep them differentiable Both of the above can be used for reconstruction, where the main goal is to explain observations through a lens of physics (hard constraint) On the other hand, generation needs generalization, and its task is to produce statistically plausible results that could be conditioned on observations (soft constraint) Both tasks are not solved yet and they can complement each other in various ways Yet another important aspect is the difference between production and execution Production = process of going from inputs to parameters Execution = process of going from parameters to result It’s important to separate these, because most usecases require fast execution to be viable which is severely constrained by the hardware So, are *world models* like Genie an important step forward? Yes Do they make other representations obsolete? Maybe some of them - but there are tons of economically valuable tasks that won’t be solved by it, at least in any observable future

Lucky Iyinbor

13,959 Aufrufe • vor 8 Monaten

📢📢 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

18,903 Aufrufe • vor 10 Monaten

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
0:35

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 Aufrufe • vor 3 Jahren

Volumetrics are amazing but historically heavy, dense, and painful to art direct. 3D Gaussian Splatting changes that by turning volumetric simulations into real-time, lightweight assets. With sufficient temporal data, these can evolve into true 4D Gaussian Splats. Even from a single static 3DGS, artists can create pseudo-4D behavior using simple deformers and procedural effects - bending, twisting, reshaping, and re-timing volumetric forms at will. This is a massive shift in how volumetrics can be captured, manipulated, and directed and also redefines them as swift real-time modular assets.
1:05

Volumetrics are amazing but historically heavy, dense, and painful to art direct. 3D Gaussian Splatting changes that by turning volumetric simulations into real-time, lightweight assets. With sufficient temporal data, these can evolve into true 4D Gaussian Splats. Even from a single static 3DGS, artists can create pseudo-4D behavior using simple deformers and procedural effects - bending, twisting, reshaping, and re-timing volumetric forms at will. This is a massive shift in how volumetrics can be captured, manipulated, and directed and also redefines them as swift real-time modular assets.

Spenser Dickerson

12,985 Aufrufe • vor 9 Monaten

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

327,373 Aufrufe • vor 2 Jahren

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

37,492 Aufrufe • vor 3 Monaten

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.
0:50

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

249,798 Aufrufe • vor 3 Jahren