Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Universal Beta Splatting Contributions: • Universal Beta Splatting: A unified N-dimensional representation with per-dimension shape control, enabling simultaneous modeling of spatial, angular, and temporal properties through anisotropic Beta kernels with spatial-orthogonal Cholesky parameterization. • Efficient CUDA implementation: Fully accelerated differentiable rendering with custom kernels, achieving real-time performance. • Interpretable... show more

MrNeRF

16,834 subscribers

10,281 Aufrufe • vor 10 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting Contributions: • MoE-GS: the first dynamic Gaussian splatting framework employing a Mixture-of-Experts architecture, enabling robust and adaptive reconstruction across diverse dynamic scenes. • A novel Volume-aware Pixel Router integrates expert outputs through differentiable weight splatting, achieving spatially and temporally coherent adaptive blending. • Efficiency of MoE-GS is improved through single-pass multi-expert rendering and gate-aware Gaussian pruning. A separate knowledge distillation strategy trains individual experts with pseudo-labels from the MoE model, enhancing quality without modifying the architecture.

MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting Contributions: • MoE-GS: the first dynamic Gaussian splatting framework employing a Mixture-of-Experts architecture, enabling robust and adaptive reconstruction across diverse dynamic scenes. • A novel Volume-aware Pixel Router integrates expert outputs through differentiable weight splatting, achieving spatially and temporally coherent adaptive blending. • Efficiency of MoE-GS is improved through single-pass multi-expert rendering and gate-aware Gaussian pruning. A separate knowledge distillation strategy trains individual experts with pseudo-labels from the MoE model, enhancing quality without modifying the architecture.

MrNeRF

10,408 Aufrufe • vor 9 Monaten

Triangle Splatting for Real-Time Radiance Field Rendering Contributions: (i) We propose Triangle Splatting, a novel approach that directly optimizes unstructured triangles, bridging traditional computer graphics and radiance fields. (ii) We introduce a differentiable window function for soft triangle boundaries, enabling effective gradient flow. (iii) We demonstrate qualitatively and quantitatively that Triangle Splatting outperforms concurrent methods in terms of visual quality and rendering speed, and achieves superior perceptual quality compared to the state-of-the-art Zip-NeRF on indoor scenes. (iv) The optimized triangles are directly compatible with standard mesh-based renderers, enabling seamless integration into traditional graphics pipelines.

Triangle Splatting for Real-Time Radiance Field Rendering Contributions: (i) We propose Triangle Splatting, a novel approach that directly optimizes unstructured triangles, bridging traditional computer graphics and radiance fields. (ii) We introduce a differentiable window function for soft triangle boundaries, enabling effective gradient flow. (iii) We demonstrate qualitatively and quantitatively that Triangle Splatting outperforms concurrent methods in terms of visual quality and rendering speed, and achieves superior perceptual quality compared to the state-of-the-art Zip-NeRF on indoor scenes. (iv) The optimized triangles are directly compatible with standard mesh-based renderers, enabling seamless integration into traditional graphics pipelines.

MrNeRF

51,407 Aufrufe • vor 1 Jahr

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.

First fully ML-framework-free 3D Gaussian Splatting implementation in LichtFeld Studio. I’ve completed the migration of the full training pipeline to a custom CUDA-based tensor library. No PyTorch, no LibTorch, no autograd. Every gradient is implemented by hand, either through CUDA kernels or minimal abstractions on top. This makes it the first full training setup for 3D Gaussian Splatting with zero dependencies on existing ML frameworks. It’s not just about independence, it's about control! We now manage every byte of GPU memory, which opens the door to tighter optimization and finer performance tuning. The framework footprint is minimal, without pulling in gigabytes of ML runtime code that was never designed for real-time or graphics-driven applications. A few modules, such as the metrics and 3DGUT interfaces, are still being ported, and some operations are temporarily naïve, so performance is not yet on par with master. But this refactor lays the groundwork for: - A fully self-contained binary - Fine-grained memory optimization - Easier experimentation without the weight of an ML stack We’re getting close.

MrNeRF

50,548 Aufrufe • vor 9 Monaten

SplatVoxel: History-Aware Novel View Streaming without Temporal Training Contributions: • We propose a hybrid Splat-Voxel feed-forward reconstruction framework that leverages historical information to enable novel view streaming, without relying on multi-view video datasets for training. • We develop an efficient sparse voxel transformer with a coarse-to-fine voxel representation, outperforming existing feed-forward Gaussian splatting methods. • Experiment results demonstrate that our proposed framework enhances novel view synthesis for streaming scene reconstruction, providing better visual quality and reduced temporal artifacts through history-aware modeling.

SplatVoxel: History-Aware Novel View Streaming without Temporal Training Contributions: • We propose a hybrid Splat-Voxel feed-forward reconstruction framework that leverages historical information to enable novel view streaming, without relying on multi-view video datasets for training. • We develop an efficient sparse voxel transformer with a coarse-to-fine voxel representation, outperforming existing feed-forward Gaussian splatting methods. • Experiment results demonstrate that our proposed framework enhances novel view synthesis for streaming scene reconstruction, providing better visual quality and reduced temporal artifacts through history-aware modeling.

MrNeRF

10,823 Aufrufe • vor 1 Jahr

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

AK

633,674 Aufrufe • vor 3 Jahren

I’ve updated my Metal spatial rendering sample to enable mixed immersion on visionOS 2 (beta), including a demonstration of how to emulate “progressive” passthrough transitions:

I’ve updated my Metal spatial rendering sample to enable mixed immersion on visionOS 2 (beta), including a demonstration of how to emulate “progressive” passthrough transitions:

Warren Moore

12,781 Aufrufe • vor 2 Jahren

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion TL;DR: Create 3/4DGS from Video Diffusion Note: Some first inference code released (not all yet). Contributions (cited): • We present DimensionX, a novel framework for generating photorealistic 3D and 4D scenes from only a single image using controllable video diffusion. • We propose ST-Director, which decouples the spatial and temporal priors in video diffusion models by learning (spatial and temporal) dimension-aware modules with our curated datasets. We further enhance the hybriddimension control with a training-free composition approach according to the essence of video diffusion denoising process. • To bridge the gap between video diffusion and real-world scenes, we design a trajectory-aware mechanism for 3D generation and an identity-preserving denoising approach for 4D generation, enabling more realistic and controllable scene synthesis. • Extensive experiments manifest that our DimensionX delivers superior performance in video, 3D, and 4D generation compared with baseline methods.

MrNeRF

17,052 Aufrufe • vor 1 Jahr

Exciting news! The Spatial Gallery app and the Apple Vision Pro app for iPhone are now available! Update to iOS 18.4 Beta 2 and visionOS 2.4 Beta 2 to try them out.

Exciting news! The Spatial Gallery app and the Apple Vision Pro app for iPhone are now available! Update to iOS 18.4 Beta 2 and visionOS 2.4 Beta 2 to try them out.

Justin Ryan ᯅ

15,536 Aufrufe • vor 1 Jahr

SuperMap: A Living Spatial Memory for Embodied AI RSS 2026 Carnegie Mellon University SuperMap is a living spatial memory for embodied AI. It perceives the world, remembers its evolution, and supports reasoning and action. It is a training-free spatio-temporal SLAM system that builds a persistent semantic world model. It fuses high-frequency geometric SLAM with asynchronous open-vocabulary perception, producing a 4D scene graph: a queryable map carrying spatial and temporal information for every object, enabling visual-language navigation and long-horizon reasoning on real robots.

SuperMap: A Living Spatial Memory for Embodied AI RSS 2026 Carnegie Mellon University SuperMap is a living spatial memory for embodied AI. It perceives the world, remembers its evolution, and supports reasoning and action. It is a training-free spatio-temporal SLAM system that builds a persistent semantic world model. It fuses high-frequency geometric SLAM with asynchronous open-vocabulary perception, producing a 4D scene graph: a queryable map carrying spatial and temporal information for every object, enabling visual-language navigation and long-horizon reasoning on real robots.

Ryohei Sasaki@engineer

24,629 Aufrufe • vor 10 Tagen

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."

MrNeRF

17,206 Aufrufe • vor 1 Jahr

Everyone's griping about different things in the Battlefield 6 Beta like performance and the movement and the hacks while I feel like the dog with a propeller hat just having fun with somehow zero issues

Everyone's griping about different things in the Battlefield 6 Beta like performance and the movement and the hacks while I feel like the dog with a propeller hat just having fun with somehow zero issues

-/Kapt’n Krunch/-

52,630 Aufrufe • vor 1 Jahr

Spectre AI Market Intelligence Platform Beta officially launches on 28.05.2026. All registered Beta users will receive platform access on this day. This marks our first live product iteration with real users - focused on community feedback, platform performance, user experience, and how people actually use market intelligence in real trading and research environments. The goal of this Beta is simple: build alongside the community, improve fast, and shape the platform around real-world usage. For security reasons, no public access links will be posted. Access will be distributed directly to approved Beta users. A major milestone for Spectre AI and the beginning of a much bigger public rollout ahead. $SPECTRE

Spectre AI Market Intelligence Platform Beta officially launches on 28.05.2026. All registered Beta users will receive platform access on this day. This marks our first live product iteration with real users - focused on community feedback, platform performance, user experience, and how people actually use market intelligence in real trading and research environments. The goal of this Beta is simple: build alongside the community, improve fast, and shape the platform around real-world usage. For security reasons, no public access links will be posted. Access will be distributed directly to approved Beta users. A major milestone for Spectre AI and the beginning of a much bigger public rollout ahead. $SPECTRE

SPECTRE AI

54,625 Aufrufe • vor 2 Monaten

Large-scale N-body simulations require the evaluation of sums involving long-range interaction kernels. Fast multipoles and Barnes–Hut methods approximate these sums in n*log(n) operations instead of n^2.

Large-scale N-body simulations require the evaluation of sums involving long-range interaction kernels. Fast multipoles and Barnes–Hut methods approximate these sums in n*log(n) operations instead of n^2.

Gabriel Peyré

74,712 Aufrufe • vor 2 Jahren

2/ Fusionist Fusionist 🛸👾 | Endurance ♠️⛓ is a blockchain game and game infrastructure layer. Recently, their beta testing got over, and beta testers were rewarded with an $ACE airdrop. Sneak peak of their beta test:

2/ Fusionist Fusionist 🛸👾 | Endurance ♠️⛓ is a blockchain game and game infrastructure layer. Recently, their beta testing got over, and beta testers were rewarded with an $ACE airdrop. Sneak peak of their beta test:

Hercules | DeFi

32,846 Aufrufe • vor 3 Jahren

🛎️ Eldora Beta is now LIVE 🛎️ Eldora Beta officially opens today, giving early users access to a unified platform to discover, manage, and interact with real tokenized RWAs in one place. 🕰️ Launch time: January 16, 2026 | 15:00 UTC 📍 Access the Beta: How to get started (2-minute setup): 1️⃣ Visit 2️⃣ Click Sign In / Sign Up 3️⃣ Enter your whitelisted email 4️⃣ Request & enter the verification code (sent to your email) 5️⃣ Set your password to complete account creation → You’re in. ⚠️ Important notes: • Access is email-specific (whitelist only) • Wallet connection is required to perform actions • Beta users help shape Eldora through real usage & feedback This is the first step toward making RWAs truly operational, not just tokenized. Welcome to Eldora Beta. Let’s build the future of on-chain real-world assets together!

🛎️ Eldora Beta is now LIVE 🛎️ Eldora Beta officially opens today, giving early users access to a unified platform to discover, manage, and interact with real tokenized RWAs in one place. 🕰️ Launch time: January 16, 2026 | 15:00 UTC 📍 Access the Beta: How to get started (2-minute setup): 1️⃣ Visit 2️⃣ Click Sign In / Sign Up 3️⃣ Enter your whitelisted email 4️⃣ Request & enter the verification code (sent to your email) 5️⃣ Set your password to complete account creation → You’re in. ⚠️ Important notes: • Access is email-specific (whitelist only) • Wallet connection is required to perform actions • Beta users help shape Eldora through real usage & feedback This is the first step toward making RWAs truly operational, not just tokenized. Welcome to Eldora Beta. Let’s build the future of on-chain real-world assets together!

Eldora

23,175 Aufrufe • vor 6 Monaten

Our Unity AI Beta will roll out with integration with the Profiler, so you can now analyze captures with AI to understand what's causing performance issues in your game.

Our Unity AI Beta will roll out with integration with the Profiler, so you can now analyze captures with AI to understand what's causing performance issues in your game.

Unity for Games

17,932 Aufrufe • vor 5 Monaten

Get ready to flex your Beta stats 💪 To get your personalized Black Ops 7 Beta Combat Record, create a post or reply below with: Call of Duty [Your Activision ID] BO7 Beta Stats

Get ready to flex your Beta stats 💪 To get your personalized Black Ops 7 Beta Combat Record, create a post or reply below with: Call of Duty [Your Activision ID] BO7 Beta Stats

Call of Duty

11,093,387 Aufrufe • vor 10 Monaten

Segment Any 3D Gaussians paper page: Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000x acceleration compared to previous SOTA.

Segment Any 3D Gaussians paper page: Interactive 3D segmentation in radiance fields is an appealing task since its importance in 3D scene understanding and manipulation. However, existing methods face challenges in either achieving fine-grained, multi-granularity segmentation or contending with substantial computational overhead, inhibiting real-time interaction. In this paper, we introduce Segment Any 3D GAussians (SAGA), a novel 3D interactive segmentation approach that seamlessly blends a 2D segmentation foundation model with 3D Gaussian Splatting (3DGS), a recent breakthrough of radiance fields. SAGA efficiently embeds multi-granularity 2D segmentation results generated by the segmentation foundation model into 3D Gaussian point features through well-designed contrastive training. Evaluation on existing benchmarks demonstrates that SAGA can achieve competitive performance with state-of-the-art methods. Moreover, SAGA achieves multi-granularity segmentation and accommodates various prompts, including points, scribbles, and 2D masks. Notably, SAGA can finish the 3D segmentation within milliseconds, achieving nearly 1000x acceleration compared to previous SOTA.

AK

69,542 Aufrufe • vor 2 Jahren

Turn regular photos into 3D Spatial photos on #iOS26 🤯 *Beta, coming to public from Autumn

Turn regular photos into 3D Spatial photos on #iOS26 🤯 *Beta, coming to public from Autumn

Safwan AhmedMia

27,999 Aufrufe • vor 1 Jahr