Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

[SIGGRAPH '24] RTG-SLAM: Real-time 3D Reconstruction at Scale Using Gaussian Splatting Paper (pdf link): Project: Code: Method ⬇️ 1 I 2

MrNeRF

16,809 subscribers

35,675 views • 2 years ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

7 Comments

MrNeRF2 years ago

2 l 2

Surgeflow2 years ago

There is something new and impressive coming out every day.

MrNeRF2 years ago

It's crazy!

Nils Pihl (broodsugar.eth)2 years ago

That’s so hot.

Tim Reha2 years ago

Super cool sweet!!

MrNeRF2 years ago

Exactly!

Antoan Bekele2 years ago

Is this actual SLAM or just reconstruction? I don't see poses or trajectory estimation.

Related Videos

WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting Project: Method ⬇️ 1 I 2

WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting Project: Method ⬇️ 1 I 2

MrNeRF

12,175 views • 1 year ago

"Subsurface Scattering for 3D Gaussian Splatting" by Jan et al. Paper: Project: Method and more beautiful results below ⬇️ 1 I 4

"Subsurface Scattering for 3D Gaussian Splatting" by Jan et al. Paper: Project: Method and more beautiful results below ⬇️ 1 I 4

MrNeRF

23,545 views • 1 year ago

Our new Gaussian point splatting renders huge 3DGS scenes in real time (e.g. 425 M⬇️). It samples pixel-sized points from the Gaussians with massive parallelism and splats them to the screen using 64-bit atomics. Grab @SIGGRAPH 2026 paper+code+video now:

Our new Gaussian point splatting renders huge 3DGS scenes in real time (e.g. 425 M⬇️). It samples pixel-sized points from the Gaussians with massive parallelism and splats them to the screen using 64-bit atomics. Grab @SIGGRAPH 2026 paper+code+video now:

Christoph Peters

22,603 views • 2 months ago

📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian splatting for 3D in the coming months. CODE RELEASED TODAY! joint work with collaborators from Université de Liège Visual Geometry Group (VGG) , KAUST Computer Vision Lab (IVUL) a thread 🧵 1/n

📢Happy to present Convex Splatting, a novel way for 3D reconstruction based on 3D smooth convexes. For the first time, a splatting-based method reaches the quality of NeRF sota methods but with real-time rendering and few primitives!! I expect this to replace Gaussian splatting for 3D in the coming months. CODE RELEASED TODAY! joint work with collaborators from Université de Liège Visual Geometry Group (VGG) , KAUST Computer Vision Lab (IVUL) a thread 🧵 1/n

Abdullah Hamdi

71,661 views • 1 year ago

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 views • 1 year ago

BIG NEWS: Introducing SDF-Splats! 🚨 I just solved one of the biggest problems in 3D Gaussian Splatting: GAPS & HOLES! 🕳️❌ My hybrid approach combines: ✨ Explicit Gaussian Splats (for detail) ✨ Implicit SDFs (for continuity) The result? Seamless 3D reconstruction with NO visible holes, NO transparency artifacts, and REAL-TIME performance at 30-60 FPS! 🔥 Traditional Gaussian Splatting looks amazing but breaks apart in under-sampled regions. SDF-Splats fills every gap using on-demand raymarching through signed distance fields—zero preprocessing, zero neural nets, pure GPU magic! ⚡ Read the full research paper: #GaussianSplatting #SDF Radiance Fields MrNeRF #RealTime3D #VR #3DReconstruction #AIResearch

BIG NEWS: Introducing SDF-Splats! 🚨 I just solved one of the biggest problems in 3D Gaussian Splatting: GAPS & HOLES! 🕳️❌ My hybrid approach combines: ✨ Explicit Gaussian Splats (for detail) ✨ Implicit SDFs (for continuity) The result? Seamless 3D reconstruction with NO visible holes, NO transparency artifacts, and REAL-TIME performance at 30-60 FPS! 🔥 Traditional Gaussian Splatting looks amazing but breaks apart in under-sampled regions. SDF-Splats fills every gap using on-demand raymarching through signed distance fields—zero preprocessing, zero neural nets, pure GPU magic! ⚡ Read the full research paper: #GaussianSplatting #SDF Radiance Fields MrNeRF #RealTime3D #VR #3DReconstruction #AIResearch

Daniel Skaale

21,031 views • 8 months ago

📢 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:

📢 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

66,590 views • 10 months ago

Meta AI strikes again, with Relightable Gaussian Codec Avatars This is an update to the Meta Codec Avatars 2.0, building on 3D Gaussian Splatting. As a result, we get fully relightable real-time avatars, accurate at the hair strand level 🤯 More details below ⬇️⬇️

Meta AI strikes again, with Relightable Gaussian Codec Avatars This is an update to the Meta Codec Avatars 2.0, building on 3D Gaussian Splatting. As a result, we get fully relightable real-time avatars, accurate at the hair strand level 🤯 More details below ⬇️⬇️

Alex Carlier

445,646 views • 2 years ago

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 views • 1 year ago

'3D Gaussian Splatting for Real-Time RF Rendering' rose to the 2nd challenge I presented. The magnifying glass isn't still crystal clear, but the result is compelling. Look at the small details/hairs on the succulent plant. Rendered in real-time. #gaussiansplatting #3D #AI

'3D Gaussian Splatting for Real-Time RF Rendering' rose to the 2nd challenge I presented. The magnifying glass isn't still crystal clear, but the result is compelling. Look at the small details/hairs on the succulent plant. Rendered in real-time. #gaussiansplatting #3D #AI

Hugues Bruyère

298,206 views • 2 years ago

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

356,366 views • 2 years ago

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction TL;DR: The first RGB-only multi-agent 3D Gaussian Splatting SLAM for collaborative photorealistic scene reconstruction. Contributions: (1) We propose the first monocular RGB-only multi-agent 3D Gaussian Splatting SLAM system. It integrates Gaussian front-ends, compact submap summaries, inter-agent verification, Sim(3) submap pose graph, and occupancy-aware fusion into a unified framework, achieving accurate tracking and photorealistic reconstruction without depth sensors. (2) We propose a Pose-Graph Bundle Adjustment (PGBA)-consistent Sim(3) loop closure mechanism for multi-agent systems, which jointly resolves intra- and inter-agent scale drift through a submap-level Sim(3) pose graph coupling geometric and photometric residuals. Robustness is ensured by a spatial-extent gate that rejects degenerate loops and an adaptive edge invalidation scheme consistent with evolving PGBA corrections. (3) We propose an occupancy-aware fusion framework for coherent multi-agent Gaussian maps. It combines occupancy-grid deduplication, decoupled coordinator, and joint pose-Gaussian photometric refinement to eliminate duplicated Gaussians, residual misalignment, and photometric seams across agents. (4) We introduce ReplicaMultiagent Plus dataset. While existing multi-agent datasets are typically limited to 2-3 agents with short trajectories, our dataset scales to 4 agents with long-horizon trajectories. In addition, we provide ground-truth geometry and semantic annotations, supporting the evaluation of monocular, RGB-D, and semantic multi-agent SLAM for collaborative dense reconstruction.

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction TL;DR: The first RGB-only multi-agent 3D Gaussian Splatting SLAM for collaborative photorealistic scene reconstruction. Contributions: (1) We propose the first monocular RGB-only multi-agent 3D Gaussian Splatting SLAM system. It integrates Gaussian front-ends, compact submap summaries, inter-agent verification, Sim(3) submap pose graph, and occupancy-aware fusion into a unified framework, achieving accurate tracking and photorealistic reconstruction without depth sensors. (2) We propose a Pose-Graph Bundle Adjustment (PGBA)-consistent Sim(3) loop closure mechanism for multi-agent systems, which jointly resolves intra- and inter-agent scale drift through a submap-level Sim(3) pose graph coupling geometric and photometric residuals. Robustness is ensured by a spatial-extent gate that rejects degenerate loops and an adaptive edge invalidation scheme consistent with evolving PGBA corrections. (3) We propose an occupancy-aware fusion framework for coherent multi-agent Gaussian maps. It combines occupancy-grid deduplication, decoupled coordinator, and joint pose-Gaussian photometric refinement to eliminate duplicated Gaussians, residual misalignment, and photometric seams across agents. (4) We introduce ReplicaMultiagent Plus dataset. While existing multi-agent datasets are typically limited to 2-3 agents with short trajectories, our dataset scales to 4 agents with long-horizon trajectories. In addition, we provide ground-truth geometry and semantic annotations, supporting the evaluation of monocular, RGB-D, and semantic multi-agent SLAM for collaborative dense reconstruction.

MrNeRF

19,357 views • 2 months ago

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 views • 1 year ago

We relived Michelangelo in neural network style!! Super excited to finally share Neuralangelo 🛠 -- 3D surface reconstruction from RGB videos with extremely high fidelity! 🤩 To appear at #CVPR2023 project page: paper: 🧵⬇️ (1/4)

We relived Michelangelo in neural network style!! Super excited to finally share Neuralangelo 🛠 -- 3D surface reconstruction from RGB videos with extremely high fidelity! 🤩 To appear at #CVPR2023 project page: paper: 🧵⬇️ (1/4)

Chen-Hsuan Lin

253,372 views • 3 years 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.

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

The greatest Gaussian Splatting VR demo ever? Captured live at NVIDIA GTC — Mariya Sha experiencing 4D Gaussian Splatting in VR for the very first time. You can tell just from her reaction that this was something else! The scene was optimized using QUEEN, NVIDIA AI Developer's advanced research project for fast radiance field rendering. It’s an incredible look at what happens when high fidelity static and dynamic gaussian splats meets VR. Watch the full video on YouTube: Robert Scoble Did you get to do this one? #VR #3D #VFX

The greatest Gaussian Splatting VR demo ever? Captured live at NVIDIA GTC — Mariya Sha experiencing 4D Gaussian Splatting in VR for the very first time. You can tell just from her reaction that this was something else! The scene was optimized using QUEEN, NVIDIA AI Developer's advanced research project for fast radiance field rendering. It’s an incredible look at what happens when high fidelity static and dynamic gaussian splats meets VR. Watch the full video on YouTube: Robert Scoble Did you get to do this one? #VR #3D #VFX

Jonathan Stephens

28,114 views • 1 year ago

Today, PlayCanvas is sharing a live demonstration of our Streaming LOD system for 3D Gaussian Splatting. Dynamically stream vast splat-based scenes of arbitrary complexity. 100% free. 100% open source. Demo link 👇 [1 / 2]

Today, PlayCanvas is sharing a live demonstration of our Streaming LOD system for 3D Gaussian Splatting. Dynamically stream vast splat-based scenes of arbitrary complexity. 100% free. 100% open source. Demo link 👇 [1 / 2]

PlayCanvas

122,711 views • 9 months ago

(1/4) Excited to share our #ICCV2023 paper Text2Room! We generate scene-scale textured 3D meshes from a given text prompt leveraging 2D text-to-image models such as StableDiffusion. Project: Code: Video:

(1/4) Excited to share our #ICCV2023 paper Text2Room! We generate scene-scale textured 3D meshes from a given text prompt leveraging 2D text-to-image models such as StableDiffusion. Project: Code: Video:

Matthias Niessner

74,905 views • 3 years ago

I 3d scanned my kid, again! Time flies fast, and now he is 7 months old. It's so exciting to preserve the memory with both 3D Gaussian Splatting and the mesh at the same time. I really wish I could render something super cool in blender, but I am so bad at it.

I 3d scanned my kid, again! Time flies fast, and now he is 7 months old. It's so exciting to preserve the memory with both 3D Gaussian Splatting and the mesh at the same time. I really wish I could render something super cool in blender, but I am so bad at it.

Chris make some 3D scans

79,119 views • 9 months ago

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS Contributions: • LangSplatV2 achieves real-time performance with 476.2 FPS for high-dimensional feature splatting and 384.6 FPS for 3D open-vocabulary text querying. • Delivers a 42× speedup and 47× boost in performance compared to LangSplat. • Improves query accuracy while drastically reducing inference time. • Replaces the heavyweight decoder in LangSplat with a sparse coefficient field, removing the main performance bottleneck. • Introduces a CUDA-optimized sparse coefficient splatting method, enabling fast and high-quality rendering of high-dimensional features. • Enables scalable 3D language interaction in complex scenes, opening up real-time applications previously not possible with LangSplat.

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS Contributions: • LangSplatV2 achieves real-time performance with 476.2 FPS for high-dimensional feature splatting and 384.6 FPS for 3D open-vocabulary text querying. • Delivers a 42× speedup and 47× boost in performance compared to LangSplat. • Improves query accuracy while drastically reducing inference time. • Replaces the heavyweight decoder in LangSplat with a sparse coefficient field, removing the main performance bottleneck. • Introduces a CUDA-optimized sparse coefficient splatting method, enabling fast and high-quality rendering of high-dimensional features. • Enables scalable 3D language interaction in complex scenes, opening up real-time applications previously not possible with LangSplat.

MrNeRF

14,261 views • 1 year ago