📢 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 #3DGSshow more

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long... Videos Contributions: • An incremental joint optimization approach for simultaneous camera pose and 3DGS reconstruction, reducing local minima and ensuring global consistency. • A robust pose estimation module leveraging learned 3D priors for accurate camera pose estimation. • An adaptive Octree Anchor Formation strategy that significantly reduces memory usage while preserving reconstruction quality.show more

"YoNoSplat: You Only Need One Model for Feedforward 3D... Gaussian Splatting" TL;DR: a unified 3D Gaussian splatting model that reconstructs high-quality scene geometry and camera poses from unposed/uncalibrated images in a single forward pass.show more

Forget about #Sora. DUSt3R is the real deal. I... took two pictures of our kitchen that barely overlap. It took << 2sec on a RTX 4090 to reconstruct it in an insane quality. Can we get out a point cloud for Gaussian Splatting #3DGS training + the camera poses?show more

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.show more

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.show more

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:show more

📢BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading We... propose a hybrid neural shading scheme for creating intrinsically decomposed 3DGS head avatars, that allow real-time relighting and animation. 🌍 📷show more

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.show more

I'm testing tree generation using only two reference images.... Basically, my Gaussian Splatting generation technique works with almost anything. I can't wait to see the final result once I’ve gathered a huge library of realistic assets for my game. For optimization, I’m planning to use a LOD system that dynamically reduces the number of Gaussian splats based on the distance from the camera.show more

Late night experiment. I built a demo that generates... 3D environments from images into 3DGS, then uses them as a spatial reference for directing real-time AR camera movements. The capture is then run through Seedance 2.0 for the final output. all running on the web via three.js↓show more

What a spot for a trail camera! We put... this camera out on a small footpath this winter for the first time just out of curiosity. We do a lot of trial and error to find good spots that wolves like to use often. The little trail is pretty close to the intersection of 3 different pack territories and we figured it might be a good place…and it was. We captured more footage of wolves and other animals on this camera that are not in this video. This video is just the highlights. Most of the other videos are at night. Notably, for every camera like this that gets great footage, we probably have 4 or 5 that are duds…and since they are duds, we don’t share that footage online!show more

Billionaire threatens workers with endless surveillance: "We're gonna put... a camera up your ass" ----- Is it that people don't want to work, or is it that they are opposed to being put under constant surveillance? Does he have a camera on him? Would he quit if he did? The people that quit sent a message that this is not acceptable to them. What would you do?show more

Proud to introduce BallerCam — an AI-powered sports camera... for families and teams. It transforms your iPhone into a smart, automated camera that records, livestreams, and saves every game. No film crew required. Just you, your phone, and the power of AI.show more

Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes Contributions: •... We propose STORM, the first feed-forward, self-supervised method for fast and accurate reconstruction of dynamic 3D scenes from sparse, multi-timestep, posed camera images. • Our bottom-up framework aggregates and transforms per-frame 3D Gaussian Splats into a cohesive scene representation, enabling self-supervised motion estimation. Furthermore, we introduce motion tokens that capture common motion primitives and regularize motion predictions, facilitating dynamic motion group segmentation without explicit motion or correspondence supervision. • We present several enhancements for in-the-wild scenarios, including sky modeling, camera exposure inconsistency handling, large novel-view extrapolation, and fine-grained human motions reconstruction, making STORM well-suited for real-world applications.show more

SukiMellow reunites with Kanel Joseph and says she has... a dark freaky side. Kanel told Suki they would talk about that off camera while they were shopping for whip cream.show more

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

Dave Franco says the animators for ‘FORGOTTEN ISLAND’ had... a camera rigged to each actors' face to animate their actual expressions. “The animators would watch that footage and match our expressions to how we were performing the lines.”show more