arXiv Machine Learning
Jun 30
DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model
arXiv:2606. 30292v1 Announce Type: new Abstract: We present DreamForge-World 0.
HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second
HyperDrone is a high‑performance quadrotor simulator that runs more than 20× faster than current batch simulators by combining optimized multirotor dynamics with the HyperLux ray‑tracing engine. HyperLux supports multiple graphics backends (Nvidia OptiX, Vulkan, Apple Metal, WebGPU) and can render RGB, depth, segmentation, normals, and optical flow at configurable fidelity—including reflections, realistic lighting, motion blur, anti‑aliasing, and PBR—while achieving millions of frames per second on consumer GPUs. The system was used to train a vision‑based yaw‑control policy in simulation, which was successfully transferred to a real Crazyflie quadrotor with an onboard camera.
Related stories
arXiv Computer Vision
Sep 14
EVIS: Real-Time Event Camera Simulation with Multimodal Supervision in NVIDIA Isaac Sim
arXiv:2607.08098v2 Announce Type: replace Abstract: Event cameras are increasingly adopted in embodied perception for their microsecond temporal resolution, high dynamic range, and resilience to moti...
arXiv AI
Jul 21
CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling
arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.
arXiv Computer Vision
Sep 28
From Mono to Stereo: Accelerating Binocular Gaussian Splatting via Reprojection and Selective Patching
The paper introduces a 2D Gaussian Splatting pipeline that renders a dominant-eye RGB image and depth proxy, then reprojects and selectively patches the affiliated eye to reduce redundant work. By reusing alpha-blending weights and generating adaptive regions of interest, the method cuts sequential binocular rendering time by 15.5% to 28.8% and GPU memory by 6% to 11% on several datasets, with minimal quality loss. It demonstrates a practical efficiency‑quality trade‑off for static‑scene stereo rendering and suggests further evaluation on dynamic scenes and VR hardware.
arXiv Computer Vision
Sep 30
PowerSim: Differentiable Physics Simulation and Rendering with Power Diagrams
arXiv:2609.38153v1 Announce Type: new Abstract: We introduce PowerSim, a method to bring physically grounded, differentiable dynamics to PowerFoam's power diagram based 3D representation. PowerSim di...
arXiv Computer Vision
Oct 21
Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game Worlds
arXiv:2610.27999v1 Announce Type: new Abstract: Moving from controllable videos to genuinely playable worlds requires persistent world state, executable game rules, and low-latency interaction. We ou...
arXiv AI
Sep 10
From Splats to Silicon: Rethinking Computational Efficiency of 3DGS
arXiv:2609.06157v1 Announce Type: cross Abstract: 3D Gaussian splatting (3DGS) represents scenes with explicit primitives and supports real-time novel-view synthesis, yet its system efficiency varies...
arXiv Computer Vision
Oct 5
Windfoil: Closed-Form Coverage for Real-Time and Differentiable Vector Graphics
Windfoil is a GPU-friendly algorithm that unifies rasterisation and differentiable vector graphics by evaluating the box-filtered winding number of quadratic Bézier contours in closed form. Implemented in WebGPU, it runs across diverse environments—from web browsers on consumer laptops to high-resolution print media—and supports real-time 2D rendering, high‑resolution rasterisation, and differentiable rendering. Compared to production engines like Skia and game‑oriented rasterisers such as Slug, Windfoil achieves closer fidelity to a reference coverage while maintaining comparable performance, and it outperforms DiffVG and Bézier Splatting in reconstruction quality at a fraction of the per‑step cost, scaling to tens of thousands of shapes at interactive rates.
arXiv Computer Vision
Oct 7
SteadySplats: Resampling of Low-Variance Gaussians for High-Fidelity Stochastic Rendering
SteadySplats introduces a method to reduce high‑frequency noise in stochastic rendering of 3D Gaussian Splatting models. The approach combines a history‑based spatial resampling scheme for faster image convergence, temporal importance resampling for camera‑movement coherence, and a color regularizer during training to lower variance along view rays. The resulting Vulkan‑based renderer achieves a 13 dB PSNR improvement over prior stochastic methods at one sample per pixel and converges quickly to a low‑error sorted 3DGS representation.
arXiv AI
Jun 16
RealityBridge: Bridging Editable 3D Gaussian Splatting Driving Simulations and Real-World Videos
arXiv:2606. 16278v1 Announce Type: cross Abstract: Long-tail hazardous scenarios are essential for safety-oriented autonomous driving, yet they are difficult to collect and reproduce at scale.
arXiv AI
Jun 4
DiffAero: A GPU-Accelerated Differentiable Simulation Framework for Efficient Quadrotor Policy Learning
arXiv:2509. 10247v1 Announce Type: cross Abstract: This letter introduces DiffAero, a lightweight, GPU-accelerated, and fully differentiable simulation framework designed for efficient quadrotor control policy learning.
arXiv Computer Vision
Sep 4
Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation
The paper introduces a large‑scale synthetic data pipeline built on Unreal Engine to generate action‑conditioned, multi‑view video for training world models. The system operates in two stages: real‑time physics simulation records trajectories, then offline rendering produces high‑quality video. It includes a distributed production framework with task partitioning, automated filtering, and a 25‑server cluster, yielding over 2,600 hours of 1080p and 6,000 hours of 720p video from 429 levels and 40 characters.