#3D spatial perception
74 related articles
·2 min
LeRobot 3D: Building 3D Spatial Perception and Manipulation for the SO101 Robot
LeRobot 3D is an open-source project adding 3D spatial perception to the SO101 robot, featuring multi-camera point cloud fusion, forward kinematics, ICP calibration, and browser-based visualization.
Read more →
·3 min
Monocular RGB Human Mesh Reconstruction: Real-Time Motion Capture at 18 FPS with Rust + CUDA
Deep dive into a real-time 3D human mesh reconstruction project using a single RGB camera, built with Rust, Candle, and CUDA, achieving 55ms/frame on RTX 5080. Exploring its architecture, Metal porting plans, and applications in VTuber, AR/VR, and sports analysis.
Read more →
·3 min
Monocular RGB Human Mesh Reconstruction: Real-Time Motion Capture at 18 FPS with Rust + CUDA
A deep dive into a real-time 3D human mesh reconstruction project using a single RGB camera, built with Rust, Candle, and CUDA, achieving 55ms/frame on an RTX 5080.
Read more →
·3 min
The Depth Perception Challenge for Transparent Objects: How LingBot-Depth Breaks Through with Masked Depth Modeling
Depth perception for transparent and reflective objects has long been a core challenge in robotic grasping. LingBot-Depth uses masked depth modeling to turn sensor failure into supervisory signals, inferring glass depth from RGB context.
Read more →
·3 min
The Depth Perception Challenge for Transparent Objects: How LingBot-Depth Breaks Through with Masked Depth Modeling
Transparent and reflective object depth perception is a core challenge in robotic grasping. LingBot-Depth uses masked depth modeling to turn sensor failure into supervision, inferring glass depth from RGB context.
Read more →
·4 min
LibTV Hands-On: A Full Breakdown of How an AI Agent Produces an Animated Short in One Day
Hands-on test of LibTV's AI Agent: from script and storyboarding to video compositing, one person completes an animated short in a day. Full breakdown of the Skill library, node workflow, and Story Board features.
Read more →
·2 min
GPT-5.6 Goes Live with Dual Quota Reset as AI Models Update Rapidly
GPT-5.6 fully launches with enhanced coding, computer operation, and long-horizon agent tasks, plus a dual quota reset. Meanwhile, ByteDance opens its C-Dance 2.5 API and Mistral debuts a single-RGB-camera natural language navigation model.
Read more →
·6 min
AI Application Engineer Interview Guide: Core Topics on Model Quantization and Inference Deployment
A systematic guide to must-know AI application engineer interview topics: PTQ/QAT quantization, operator fusion, inference pipelines, latency/throughput analysis, and edge deployment of detection/segmentation/BEV models.
Read more →
·6 min
AI Application Engineer Interview Guide: Core Topics in Model Quantization and Inference Deployment
A systematic review of must-know topics for AI Application Engineer interviews: PTQ/QAT quantization, operator fusion, inference pipelines, latency/throughput analysis, and edge deployment of detection/segmentation/BEV models.
Read more →
·7 min
DeepSeek's Mysteriously Retracted Paper: Breaking AI's Multimodal Reasoning Bottleneck with Visual Primitives
DeepSeek's paper 'Thinking with Visual Primitives' was online for just 4 hours before being pulled. It uses bounding boxes and points as reasoning primitives, letting models 'point at' images to outperform GPT, Gemini, and Claude on maze navigation and counting.
Read more →
·6 min
Tongyi Qianwen Qwen-Image-3.0: The Leap of AI Image Generation from Toy to Productivity Tool
Tongyi Qianwen Qwen-Image-3.0 image generation model gets a comprehensive upgrade: supporting 4,500-token ultra-long instructions, pixel-level detail rendering, 12-language knowledge understanding, and ancient painting restoration. This article analyzes its three core capabilities.
Read more →
·7 min
Alibaba Open-Sources 2.4T Qwen Model as Chinese AI Sweeps the Global Competitive Landscape
Alibaba open-sources a 2.4 trillion parameter Qwen model and launches the Qwen Token Plan. Chinese models surge, Kimi K3 tops global rankings, and China's AI is reshaping the global competitive landscape.
Read more →
·3 min
Claude Sonnet 5 Deep Dive: Impressive Benchmarks, Disappointing Reality — Stick with OPUS 4.8
Anthropic's Claude Sonnet 5 claims near-OPUS 4.8 performance at lower cost. Real-world tests reveal hidden tokenizer costs, weak creative output, and only 13th place on Cursor rankings.
Read more →
·2 min
Gemini 3.5 Pro Rebuilt from Scratch: Delays, Talent Exodus, and the AI Competition Landscape
Gemini 3.5 Pro was rebuilt from scratch due to gaps in math reasoning and SVG generation, as four senior Google researchers joined Anthropic. A deep dive into the technical and talent implications.
Read more →
·2 min
Getting Started with ROS2: What Is a Robot Operating System, and How Does It Differ from ROS1?
A beginner's guide to ROS2: what ROS really is (an SDK, not a traditional OS), how ROS1 and ROS2 differ, and how to choose the right version to start robot development.
Read more →
·2 min
How GPT-Live Solves the Cocktail Party Problem in Voice AI
OpenAI's GPT-Live voice model tackles the cocktail party problem through Background Robustness — enabling precise speaker focus in noisy, multi-person environments with natural multi-turn dialogue.
Read more →
NVIDIA DeepStream 9.1 Multi-Camera 3D …
·2 min
NVIDIA DeepStream 9.1 Multi-Camera 3D Tracking: Principles, Architecture, and Applications
A deep dive into NVIDIA DeepStream 9.1 multi-camera 3D tracking: cross-camera Re-ID, 3D coordinate fusion, GPU-accelerated pipelines, and real-world deployments in retail, warehousing, and security.
Read more →
GitHub Daily · July 18: 3D Reconstruct…
·3 min
GitHub Daily · July 18: 3D Reconstruction Foundation Model Tops the Charts, AI Engineering and CLI Agents Explode Collectively
July 18 GitHub Daily: 3D reconstruction foundation model lingbot-map tops the charts, with AI engineering tooling, CLI Agents, and the MCP ecosystem exploding across the board.
Read more →
·6 min
Multimodal and Embodied Intelligence: A Comprehensive Look at Progress, Pitfalls, and Opportunities
At the Microsoft Research India summit, top experts explore the real progress of multimodal AI and embodied intelligence: fusing classical robotics with large models, healthcare AI deployment challenges, perceptual bottlenecks in reasoning, and possibilities beyond scaling.
Read more →
·3 min
A $120 Robot Arm Learns to Actively Search: How Squint Breaks the Field-of-View Barrier
Squint open-source research enables a $120 SO-101 arm to search beyond its camera FOV using 16×16 pixel input, achieving 100% success in 24 min on an RTX 4060.
Read more →