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。

𝗜𝗻𝘁𝗿𝗼𝗱𝘂𝗰𝗶𝗻𝗴 𝗨𝗩𝗚𝗦 We introduce 𝗨𝗩𝗚𝗦, a new 2D representation of 3D Gaussian Splatting (3DGS) that leverages spherical mapping. Website: Paper:

Nikolaos Sarafianos

1,237 subscribers

10,715 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

7 条评论

Nikolaos Sarafianos 的头像

Nikolaos Sarafianos1 年前

- UVGS enables the application of image-based models for 3DGS feature extraction by representing it as multi-channel images. - We demonstrate effective compression of heterogeneous UVGS features and successful generalization of pre-trained 2D VAEs to this new representation.

Nikolaos Sarafianos 的头像

Nikolaos Sarafianos1 年前

- Our new UVGS representation makes it effortless to leverage foundational 2D models, such as diffusion models, to directly generate 3DGS. Work with colleagues at Brown and Meta Reality Labs

David 的头像

David1 年前

really cool!

Ziyu Wan 的头像

Ziyu Wan1 年前

Impressive work!!! 🚀 Would love to see how this approach connects with our prior work 'Omage' ( - particularly regarding patch-structured UV mapping!

Nikolaos Sarafianos 的头像

Nikolaos Sarafianos1 年前

I actually presented Omages (along with Geometry Image Diffusion from @DoctorDukeGonzo ) this week at a reading group; I really like this line of work. We'll be updating the arxiv in the next few days so we'll include a discussion related to Omages. See you in Singapore :)

Spenser Dickerson 的头像

Spenser Dickerson1 年前

Very interesting!

Heshim🔥📛 的头像

Heshim🔥📛1 年前

Can you train a generative AI on these 2d representations? Just to generate a family of odd 3d shapes and see what happens? For example, gather many 2d representations of cars… train an image model to generate these 2d multi channel images… then see what they look like in 3d?

相关视频

Gaussian Shell Maps are a new neural scene representation that connects fields and 3D Gaussians. This representation unlocks the full potential of 3D Gaussian splatting for generative AI applications, such as 3D avatar generation. 1/2

Gordon Wetzstein

52,480 次观看 • 2 年前

I am releasing the “MLSharp” app for macOS. MLSharp is a premium macOS application that transforms 2D images into immersive 3D Gaussian Splatting (3DGS) models using state-of-the-art AI.

I am releasing the “MLSharp” app for macOS. MLSharp is a premium macOS application that transforms 2D images into immersive 3D Gaussian Splatting (3DGS) models using state-of-the-art AI.

むっちゃん

90,906 次观看 • 3 个月前

Excited to share our new #SIGGRAPH2025 paper! In this work, we show how to combine Gaussian splatting and computer-generated holography using Gaussian Wave Splatting. This enables photorealistic 3D holograms for emerging holographic VR/AR displays. 1/4

Excited to share our new #SIGGRAPH2025 paper! In this work, we show how to combine Gaussian splatting and computer-generated holography using Gaussian Wave Splatting. This enables photorealistic 3D holograms for emerging holographic VR/AR displays. 1/4

Gordon Wetzstein

21,220 次观看 • 1 年前

GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views TL;DR: Are we witnessing the first steps towards 3DGS live streaming? Contributions: • We introduce a generalizable 3D Gaussian Splatting methodology that employs pixel-wise Gaussian parameter maps defined on 2D source image planes to formulate 3D Gaussians in a feed-forward manner. • We propose a fully differentiable framework composed of an iterative depth estimation module and a Gaussian parameter regression module. The intermediate depth prediction bridges the two components and allows them to benefit from joint training. • We introduce a regularization term and an epipolar attention mechanism to preserve geometry consistency between the two source views when using only rendering loss. Our method generalizes well to unseen characters even in complicated scenes. • We develop a real-time FVV system that achieves high-resolution rendering of characters in the scene without any geometry supervision.

GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views TL;DR: Are we witnessing the first steps towards 3DGS live streaming? Contributions: • We introduce a generalizable 3D Gaussian Splatting methodology that employs pixel-wise Gaussian parameter maps defined on 2D source image planes to formulate 3D Gaussians in a feed-forward manner. • We propose a fully differentiable framework composed of an iterative depth estimation module and a Gaussian parameter regression module. The intermediate depth prediction bridges the two components and allows them to benefit from joint training. • We introduce a regularization term and an epipolar attention mechanism to preserve geometry consistency between the two source views when using only rendering loss. Our method generalizes well to unseen characters even in complicated scenes. • We develop a real-time FVV system that achieves high-resolution rendering of characters in the scene without any geometry supervision.

MrNeRF

25,862 次观看 • 1 年前

📢 We introduce PPISP, a physically plausible camera module for Gaussian Splatting that reduces floaters under varying appearance and predicts camera corrections for novel views such that they closely match what a real camera would output. #CV #3DGS

📢 We introduce PPISP, a physically plausible camera module for Gaussian Splatting that reduces floaters under varying appearance and predicts camera corrections for novel views such that they closely match what a real camera would output. #CV #3DGS

Zan Gojcic

26,233 次观看 • 6 个月前

Happy to introduce Habitat-GS, a non-intrusive extension of Habitat-Sim that brings dynamic Gaussian Splatting for photorealistic rendering and comes with hundreds of high-quality 3DGS scene assets, aiming to empowering navigation research. Code:

Happy to introduce Habitat-GS, a non-intrusive extension of Habitat-Sim that brings dynamic Gaussian Splatting for photorealistic rendering and comes with hundreds of high-quality 3DGS scene assets, aiming to empowering navigation research. Code:

Sida Peng

11,997 次观看 • 3 个月前

Hosting a 3D Gaussian Splatting study session soon. Made a quick video comparing point cloud vs Gaussian Splats vs trained result, all with the same number of points. Hope it sparks some interest in #3DGS among the attendees.

Hosting a 3D Gaussian Splatting study session soon. Made a quick video comparing point cloud vs Gaussian Splats vs trained result, all with the same number of points. Hope it sparks some interest in #3DGS among the attendees.

Takashi Yoshinaga

17,593 次观看 • 3 个月前

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video Contribution quote from the paper: In summary, our main contributions are • a comprehensive pipeline for reconstructing the shape, appearance, and behavior of real-world garments using Gaussian splatting, • an algorithm for registering garment meshes to multi- view videos with an optimization procedure based on Gaussian splatting, and • a Gaussian Garment representation that combines triangle meshes with Gaussian textures to capture photorealistic appearance and can be used as a fully controllable 3D asset.

MrNeRF

27,277 次观看 • 1 年前

Happy to announce the results of our latest research, which takes 3D Gaussian Splatting to the next level: "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets," which has been accepted at #SIGGRAPH2024!🎉 Find it here:

Happy to announce the results of our latest research, which takes 3D Gaussian Splatting to the next level: "A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasets," which has been accepted at #SIGGRAPH2024!🎉 Find it here:

Bernhard Kerbl

356,395 次观看 • 2 年前

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

140,992 次观看 • 2 年前

RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting Contributions: • We introduce a unified surface-volume Gaussian scene representation for jointly modeling sharp specular reflections and clear transmission in real-world scenes containing thin semi-transparent surfaces. • We propose Specular-Aware Gradient Gating to suppress misleading gradients from complex specular regions, substantially reducing floaters in the transmission branch. • Extensive experiments demonstrate that RT-Splatting significantly outperforms prior methods while maintaining real-time rendering and enabling flexible scene editing.

RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting Contributions: • We introduce a unified surface-volume Gaussian scene representation for jointly modeling sharp specular reflections and clear transmission in real-world scenes containing thin semi-transparent surfaces. • We propose Specular-Aware Gradient Gating to suppress misleading gradients from complex specular regions, substantially reducing floaters in the transmission branch. • Extensive experiments demonstrate that RT-Splatting significantly outperforms prior methods while maintaining real-time rendering and enabling flexible scene editing.

MrNeRF

28,296 次观看 • 2 个月前

📢 I’m testing ViggleAI new AI tool, PINOC, and it’s seriously impressive. You can create 3D Gaussian splatting models from just one image and animate them with a video! It’s the first AI I’ve tried that can animate Gaussian splatting models. I also talked to someone from Viggle, and they might add the option to import your own Gaussian splatting models and animate them. If that happens, I’ll probably make a video tutorial showing how to boost the detail level of a Gaussian splatting model by 4x to create highly realistic animated characters.

📢 I’m testing ViggleAI new AI tool, PINOC, and it’s seriously impressive. You can create 3D Gaussian splatting models from just one image and animate them with a video! It’s the first AI I’ve tried that can animate Gaussian splatting models. I also talked to someone from Viggle, and they might add the option to import your own Gaussian splatting models and animate them. If that happens, I’ll probably make a video tutorial showing how to boost the detail level of a Gaussian splatting model by 4x to create highly realistic animated characters.

Alex

29,776 次观看 • 2 个月前

3D Gaussian Splatting can struggle with highly specular surfaces. But this is perhaps the best 3DGS of a watch that I've seen. It even does a decent job with the Cyclops lens. This is 11MB. With the upcoming SOGS integration in SuperSplat, it will be 3MB!

3D Gaussian Splatting can struggle with highly specular surfaces. But this is perhaps the best 3DGS of a watch that I've seen. It even does a decent job with the Cyclops lens. This is 11MB. With the upcoming SOGS integration in SuperSplat, it will be 3MB!

Will Eastcott

21,294 次观看 • 1 年前

A drone scan of the partial glacier collapse in Blatten, reconstructed using 3D Gaussian Splatting. New approaches to disaster visualization can provide a rapid overview of the situation.

A drone scan of the partial glacier collapse in Blatten, reconstructed using 3D Gaussian Splatting. New approaches to disaster visualization can provide a rapid overview of the situation.

MrNeRF

24,208 次观看 • 1 年前

We are developing a custom Gaussian Splatting Viewer, which enables to compare different models side by side in a single interface. Online soon The 3d model generated by the new polycam

We are developing a custom Gaussian Splatting Viewer, which enables to compare different models side by side in a single interface. Online soon The 3d model generated by the new polycam

Center for Spatial Technologies

14,217 次观看 • 2 年前

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

📢📢 𝐆𝐚𝐮𝐬𝐬𝐢𝐚𝐧𝐒𝐩𝐞𝐞𝐜𝐡: Audio-Driven Gaussian Avatars 📢📢 We synthesize photorealistic and 3D-consistent talking human head avatars driven directly from spoken audio. More specifically, we introduce an efficient 3DGS-based representation, combined with an audio-conditioned transformer, to generate realistic and high-quality animations. Our method can easily generalize to a variety of in the wild scenarios like songs, foreign languages etc. We further introduce a new multiview dataset of native English speakers with overall recording time of ∼3.5 hours. Project: Video: Great work by Shivangi, Artem Sevastopolsky, Tobias Kirschstein, Justus Thies, Angela Dai

Matthias Niessner

22,641 次观看 • 1 年前

HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting Contributions: First, we propose Homogeneous Gaussian Splatting (HoGS), a novel method adopting homogeneous coordinates to represent positions and scales of 3DGS for realistic and real-time rendering of both near and far objects. Second, despite the ultimate simplicity of HoGS, our method achieves state-of-the-art NVS results compared to other implicit and explicit representations.

HoGS: Unified Near and Far Object Reconstruction via Homogeneous Gaussian Splatting Contributions: First, we propose Homogeneous Gaussian Splatting (HoGS), a novel method adopting homogeneous coordinates to represent positions and scales of 3DGS for realistic and real-time rendering of both near and far objects. Second, despite the ultimate simplicity of HoGS, our method achieves state-of-the-art NVS results compared to other implicit and explicit representations.

MrNeRF

22,978 次观看 • 1 年前

$DreamScene360 Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360^{circ} scene generation pipeline$

DreamScene360 Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting The increasing demand for virtual reality applications has highlighted the significance of crafting immersive 3D assets. We present a text-to-3D 360^{circ} scene generation pipeline

AK

24,910 次观看 • 2 年前

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,736 次观看 • 1 年前

📸 A few photos. ⚡ A few seconds. A high-quality 3D scene！🎬 Meet Topos-Lite, our new 3D Gaussian Splatting model. With just a few sparse multi-view images, it can generate a high-quality, renderable 3D scene in few seconds We’re excited to share more soon. The technical report is coming shortly — stay tuned and stay in touch. 👀 #ToposLite #3DGS #3DGeneration #SpatialAI #AIGC #photograph #3DArtwork

📸 A few photos. ⚡ A few seconds. A high-quality 3D scene！🎬 Meet Topos-Lite, our new 3D Gaussian Splatting model. With just a few sparse multi-view images, it can generate a high-quality, renderable 3D scene in few seconds We’re excited to share more soon. The technical report is coming shortly — stay tuned and stay in touch. 👀 #ToposLite #3DGS #3DGeneration #SpatialAI #AIGC #photograph #3DArtwork

InSpatio｜影溯

22,386 次观看 • 21 天前