#3D Gaussian Splatting (50)

Genesis AI's open simulation platform for physical AI: one Pythonic API over a multi-physics engine (rigid, FEM, MPM, PBD, SPH, Stable Fluid, IPC), the Nyx path tracer, and Quadrants, a cross-platform Python-to-GPU compiler. It is built to be the evaluation engine for robot foundation models rather than a data factory: 30,000 parallel environments at 43M FPS, and under a zero-shot real-to-sim protocol, sim-vs-real evaluation agreement of Pearson 0.8996 with mean maximum rank violation 0.0166. Apache 2.0, 29.9k stars.

SimulationPhysics EngineEmbodied AI

Python30k2.9k224

1:00

GaussiAnimate: Compressing 4D Capture Into a Rigged 3D Asset with Secondary Dynamics

@yuliangxiu · 197 views · 2026-10-11

GaussiAnimate4D Capture3D Gaussian Splatting

0:04

Real-Time Neural Rendering for World Models

@christiansafka · 264 views · 2026-10-06

Neural rendering3D Gaussian SplattingWorld Models

GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping

MIT presents GaussLite, the first 3DGS mapping system that takes a natural-language task and allocates representation capacity online by task relevance: a one-shot LLM parser extracts target and anchor objects, Grounding DINO + FastSAM ground them per frame into relevance masks that steer seeding density, gradient flow and initial scale. At matched Gaussian budget and real-time 4 Hz mapping, ROI PSNR improves by +2.72 dB on Replica and +2.23 dB on real campus scenes; multi-agent maps fuse via per-voxel voting on active-optimization counts, beating concatenation by +3.42 dB while sharing only 7.08% of the map.

Thomas, Annika, Peterson, Mason, How, Jonathan P. · 608 views · Jun 29, 2026

3D Gaussian SplattingSLAMRobotic MappingJun 29, 2026

FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction

Existing occupancy prediction relies on large-scale voxel annotations and generalizes poorly across environments, collapsing to near-zero per-class scores on unseen scenes. FreeOcc is the first training-free framework for open-vocabulary occupancy prediction: a SLAM backbone supplies poses and sparse geometry, geometrically anchored Gaussian updates build a dense 3DGS map (ray-aligned anisotropic initialization with s_parallel = gamma * s_perp and Gaussian centers fixed to SLAM points), an off-the-shelf vision-language model attaches open-vocabulary semantics to Gaussian primitives, and a probabilistic Gaussian-to-occupancy projection yields a voxel field queryable online, with no learnable parameter serving the occupancy task. On EmbodiedOcc-ScanNet it reaches 31.29/13.86 monocular and 34.40/15.84 RGB-D IoU/mIoU, more than double the self-supervised baselines; geometric IoU improves 76.1% over the next-best DROID-Splat. The paper also introduces ReplicaOcc, where learned baselines collapse to 0.00-0.01 while FreeOcc transfers zero-shot to 55.65/20.90 and runs online at 25 FPS on a live RealSense D435i stream.

Jiang, Zeyu, Zhou, Changqing, Zuo, Xingxing · 794 views · Apr 30, 2026

3D Gaussian SplattingOccupancy PredictionSLAMApr 30, 2026

3:31

Splat-MOVER: A Robot That Updates Its 3D World After Every Move

@Alacritic_Super · 667 views · 2026-09-20

3D Gaussian SplattingRobotic ManipulationGrasp Generation

1:04

SceneAgent: 3D Captures Into Sim Scenes With Predictive Physics

@hankyang94 · 667 views · 2026-09-18

Simulation3D Gaussian SplattingScene Generation

LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World

Training vision-language-action (VLA) policies for humanoid loco-manipulation is constrained by the high cost and complexity of collecting human teleoperation demonstrations. VLA policies fine-tuned in simulators have, until now, failed to transfer effectively in humanoid loco-manipulation tasks. We present LEGS (Loco-manipulation via Embodied Gaussian Splatting), a hybrid simulator that composites a mesh foreground (robot, objects, props) over a photorealistic 3D Gaussian Splatting (3DGS) background reconstructed from a handheld scene capture. LEGS uses a procedural motion-primitive generator to synthesize labeled demonstrations at scale without human teleoperation, and a deterministic two-stage color calibration to align the rendered 3DGS image to the robot's deployment camera. On a Unitree G1 humanoid robot, across three pick-and-place tasks of increasing whole-body difficulty and three VLA backbones (psi_0, pi_0.5, GR00T N1.6), a policy trained purely on LEGS data matches or exceeds one trained on human teleoperation demos on every experiment. It also outperforms a mesh-only simulation baseline that ablates the effect of the 3DGS background, showing that photorealistic rendering is a key enabler for synthetic data transfer. Humanoid motion is recorded independently of scene appearance in LEGS, allowing the same auto-generated demonstrations to be re-rendered under new backgrounds and object meshes–covering a new scene at more than 15x lower cost than teleoperation–to augment training data for robustness to scene variations. Under combined object-and-scene appearance shift, the policy trained on re-rendered LEGS-AUG data maintains task success while the baseline trained on teleoperation data fails entirely. Our project page is located at https://legsvla.github.io/.

Kim, Hojune, Chen, Timothy, Sun, Jiankai · 867 views · May 31, 2026

HumanoidVLA3D Gaussian SplattingMay 31, 2026

1:07

WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild

3D Gaussian Splatting (3DGS) delivers real-time and high-fidelity rendering but remains challenged by unconstrained in-the-wild scenes, where drastic appearance variations and transient objects violate multi-view consistency. Existing methods are fundamentally limited by independent and discrete embeddings that struggle to capture continuous environmental changes or model spatially-varying local illumination. To address these limitations, we propose WilLaGS, a unified framework for robust 3D scene reconstruction and generative appearance synthesis under unconstrained settings. Specifically, we introduce a generative appearance model where a β-VAE learns a structured and continuous manifold of global appearance. Conditioned on the latent code, we construct a 3D neural appearance field that generates dynamic Tri-Plane features to encode spatially-varying local illumination effects. Furthermore, to suppress transient artifacts, we present a self-supervised perceptual masking mechanism that leverages a Teacher-Student (EMA) architecture to derive a stable scene consensus, robustly identifying inconsistent regions via perceptual discrepancies. Extensive experiments on multiple datasets demonstrate that WilLaGS achieves state-of-the-art performance in reconstruction quality and novel view appearance synthesis, while maintaining real-time rendering efficiency.

Yuhao Bai, Qianqiu Tan, Lilong Chen · 693 views · Aug 28, 2026

3D Gaussian SplattingGaussian Splattingβ-VAEAug 28, 2026

DL-SLAM: Enabling High-Fidelity Gaussian Splatting SLAM in Dynamic Environments based on Dual-Level Probability

Recent advances in 3D Gaussian Splatting (3DGS) have enabled significant progress in dense dynamic Simultaneous Localization And Mapping (SLAM). Prevailing methods typically discard predefined dynamic objects, ignoring that transiently static objects offer valuable geometric constraints for pose estimation. A recent work attempts to leverage this potential by employing per-pixel uncertainty maps to quantify the magnitude of motion. While this approach enables transiently static objects to enhance pose estimation, it erroneously integrates these objects into the static map, resulting in persistent artifacts. Moreover, its reliance on purely geometric information leads to ambiguous object boundaries in the uncertainty maps. To overcome these limitations, we present DL-SLAM, a monocular Gaussian Splatting SLAM system built upon a novel dual-level probabilistic framework. Our method computes dynamic probability maps by combining semantic and geometric information. These pixel-level probabilities are lifted to 3D and aggregated to derive an object-level dynamic probability for each instance. Object-level probability enables the categorical pruning of dynamic Gaussians, resulting in an artifact-free static map. The static map, in turn, provides a geometrically consistent guidance to refine the pixel-wise probabilities, enhancing their reliability. Experimental results demonstrate that DL-SLAM outperforms existing approaches, improving tracking accuracy by up to 13% while generating high-fidelity semantic maps.

Ziheng Xu, Qingfeng Li, Xuefeng Liu · 623 views · Jul 2, 2026

Dynamic EnvironmentSLAM3D Gaussian SplattingJul 2, 2026

Bringing 3DGS into NVIDIA Isaac Sim: A Photoreal Import Workflow and Four Industrial-Simulation Weaknesses

How to import 3DGS scans into Isaac Sim 6.0: the silent 2^24 point cap, USD conversion, orientation fixes, trajectory cameras — plus four industrial weaknesses and mesh-based workarounds.

BLOG

3D Gaussian SplattingIsaac SimUSDLocaHun 3DSimulation Environment

Setting Up a 3DGS Simulation Environment for Isaac Sim: Untouched Scan Data, Ground-Hole Patches, and a PhysX Vehicle in Three Steps

Using Shibuya's scramble crossing as a case study: keep the scanner's 3DGS and mesh untouched, patch only the ground holes from measured LiDAR, stack appearance and physics as two layers, and drive a PhysX Vehicle in Isaac Sim.

BLOG

3D Gaussian SplattingIsaac SimLiDARPhysX VehicleLocaHun 3D

VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes

VLK synthesizes paired vision-language-kinematics supervision inside 3DGS-reconstructed real scenes: it generates navigation and object-interaction trajectories with privileged scene info, renders egocentric views after the fact, and produces 48,000 paired trajectories to train a policy predicting Unitree G1 whole-body motion, enabling sim-to-real perception-based humanoid loco-manipulation.

Yen-Jen Wang, Jiaman Li, Sirui Chen · 595 views · Jun 29, 2026

HumanoidLoco-manipulationSynthetic DataJun 29, 2026

0:37

DeWorldSG: Probabilistic 3D Gaussian Scene Graph Generation (ECCV 2026)

@tokufxug · 512 views · 2026-08-14

Scene graphs3D Gaussian SplattingWorld Models

0:20

Stipple: Real-Time Incremental Gaussian Splatting with Visual-Inertial Tracking

@mateodemayo · 454 views · 2026-08-13

SLAMGaussian SplattingVisual Inertial

1:02

DJI and XGRIDS air-ground 3DGS map fusion

@DuckbillStudio · 508 views · 2026-08-12

3D Gaussian SplattingDJIMatrice 4E

0:34

DJI M4E and PortalCam air-ground 3DGS map fusion

@DuckbillStudio · 509 views · 2026-08-07

3D Gaussian SplattingDJI Matrice 4EPortalCam

TRACE: Ergodic Trajectory Optimization for Active Scene Reconstruction

Existing active reconstruction systems with Gaussian-splatting maps select observations greedily, optimizing a single next-best-view (NBV) at each step and connecting the chosen views by short-horizon path planning. This greedy decoupling disregards the global structure of scene information, producing inefficient trajectories that waste sensing capacity in transit between selected views. In this work, we study active reconstruction as an ergodic coverage problem: the time-averaged spatial statistics of the sensor trajectory should match a target information distribution induced by the current map. Our approach derives this target distribution online from uncertainty and visibility, and calculates ergodic trajectories via a kernel-ergodic horizon planner with gradient flow and footprint depletion, closing the loop between mapping and trajectory optimization. We thoroughly evaluate TRACE on the Replica dataset against the Next-Best-View (NBV) baselines, improving PSNR by 1.5 dB. Code: https://github.com/spikelab-jhu/trace-active-reconstruction.

Ziyue Zheng, Linli Shi, Bingkun He · 479 views · Aug 3, 2026

3D Gaussian SplattingNBVTRACEAug 3, 2026

StreamSplat: Streaming Feed-Forward 3D Gaussian Splatting

Feed-forward 3D Gaussian Splatting enables efficient novel-view synthesis without per-scene optimization, but most existing methods assume a fixed set of context views and process them jointly. This limits their applicability to online scenarios where calibrated views arrive sequentially and the scene must be updated causally. We present StreamSplat, a streaming feed-forward 3DGS framework that incrementally maintains a persistent geometry-grounded scene state and decodes it into renderable 3D Gaussians after each input chunk. StreamSplat centers on a Voxel-Aligned Causal Cache (VACC), which stores historical 3D tokens in a memory-bounded voxel structure so that memory grows with explored scene geometry rather than stream length. To better reuse history during causal prediction, we introduce History-Projected Depth Anchoring (HPDA) to project cached geometry as depth guidance for current cost-volume estimation, and Cache-Guided Feature Injection (CGFI) to inject cached latent evidence into Gaussian-token regression. Experiments on DL3DV, RealEstate10K, and ScanNet show that StreamSplat remains competitive with state-of-the-art feed-forward 3DGS methods under sparse causal inputs, despite not using future views or full-scene context. More importantly, it scales to long input streams with 256, 512, and 1024 views where fixed-view baselines run out of memory, yielding sustained improvements in novel-view synthesis quality as more observations arrive. The code will be made publicly available upon acceptance.

Changhao Song, Yuxuan Wang, Qibiao Li · 416 views · Aug 3, 2026

3D Gaussian Splatting3D reconstructionStreaming InferenceAug 3, 2026

1:08

UnrealTwin: 36M Splat 3D Snow Simulation on WebGPU

@tokufxug · 353 views · 2026-08-03

WebGPU3D Gaussian SplattingUnrealTwin