I always thought camera pose estimation is necessary for... 3D reconstruction, until Zequn and Stephen proved me wrong! Introducing PreF3R, purely feed-forward 3D Gaussian Splatting without any intermediate pose estimation and COLMAP initialization. Video in, 3D Gaussians and novel view rendering out. Key technique: spatial memory network from Spann3R and Gaussian head supervised by pointmap loss plus photometric loss. See more at:show more

F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Consistent Gaussian... Splatting Contributions: • We pioneer 3D-aware generation using generalizable feed-forward Gaussian Splatting representation, achieving significant efficiency and favorable rendering quality on monocular datasets. • We significantly advance the capability of pixel-aligned Gaussian Splatting representations by designing a self-supervised cycle training strategy specifically tailored for monocular datasets. • We further mitigate the artifacts of 3D-aware representations caused by large viewpoint shifts by introducing geometry-aware video priors.show more

Introducing pixelSplat: feed-forward Gaussian splats from image pairs! Led... by David Charatan and Lester Li, collaborating with Andrea Tagliasacchi 🇨🇦! We propose a memory-efficient, fast and editable alternative to pixelNeRF based on 3D Gaussian Splatting! 1/nshow more

Discover the right 3D Geometric Foundation Model for your... task—whether it’s stereo matching, multi-view depth estimation, video depth, pose estimation, semantic understanding, or novel view synthesis. Explore more insights in our #E3DBench #FoundationModel #3D #GaussianSplatting. Project Webpage:show more

Apple just trained a 3D Gaussian head reconstruction model... on 10,000+ subjects. Feed-forward. No test-time optimization. New identity in, reconstructed Gaussian head out. The UV-parameterized Gaussian representation decouples the number of Gaussians from the number and resolution of input images, making it practical to train with many high resolution views. And the heads are not just static either: text-conditioned identity generation, plus blendshape-driven latent animation across identities. We've been building in the 3D Gaussian Splatting space for a while. The gap between "research demo" and "works on real people at scale" is closing fast.show more

Recently, I've been working a lot on Gaussian Splatting.... I built a repo for camera pose estimation using Rerun, Gradio, and prefix.dev that merges GLOMAP with hloc! 🧵More info belowshow more

NeuralGS Bridging Neural Fields and 3D Gaussian Splatting for... Compact 3D Representationsshow more

Monocular pose estimation has gotten really good Grab any... 2D video and transfer the performance to a 3D charactershow more

LGTM from Apple: 4K feed-forward 3D Gaussian Splatting. instant... 4K 3D scenes without massive GPUs.. - predicts a few lightweight 3D shapes, wraps them in ultra-high-res 2D textures. - low Memory usage You take two normal photos of a room. Instantly walk around it in flawless 3D.show more

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from... In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.show more

I implemented 3D Gaussian Splatting in WebGL. Check it... out here:show more

Learn how to combine a deep learning model for... pose estimation to perform a 3D reconstruction using two cameras 📸show more

"Spann3R: 3D Reconstruction with Spatial Memory" In a nutshell:... DUSt3R strikes again! Paper: Project: Method ⬇️show more

yoooooo.... 3D gaussian splatting + simulated kinematics

Gaussian Painters imported into #b3d as ellipsoids (3D Gaussian... Splatting plugin for Blender - work in progress)show more

Wonderland: Navigating 3D Scenes from a Single Image Contributions:... • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.show more

3D Gaussian Splatting with Unity VFX Graph

Meet 3D Gaussian Splatting - a 3D AI breakthrough... that’s changing the game for real-time 3D rendering. It generates 3D world with state-of-the-art visuals at fast speeds: 100+ fps at 1080p. Here’s the magic behind it:show more

Tune in @ ICCV on Mon @ 10.30am where... I talk about everything 3D + Realism: - Hyperscape: Gaussian Splatting in VR - FlowR: Flowing from Sparse-2-Dense 3D Recon - BulletGen: Improving 4D Recon with Bullet-Time Gen - MapAnything: Universal Feed-Forward Metric 3D Recon 🧵👇show more

Who needs a mocap suit? 😁Testing out AIOS -... All-in-One-Stage Expressive Human Pose and Shape Estimation (link in thread). I uploaded a video from Pexels and it created the 3D mesh, which I was able to import into Blender and use Geometry nodes to control. (see thread for nodes).show more