Core Technology

DexForce' s world-class team leads in AI, computer vision, generative 3D, and 3D perception large models. Frontier research drives our DexVerse™, AI, and synthetic data engine to realize general robot intelligence.

Latest Report

Dexterity-BEV: Scaling up Dexterous Manipulation Learning with BEV Alignment

Before generalist policies emerge, heterogeneous robot data are to be unified as the right and
effective representation.

Learn More

DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks

Learn More

EmbodiChain

Automated, Efficient, and Modular Platform for Scaling Up Embodied AI Learning

Learn More

Technical Literature

Technological Achievements

Champion of the 1st WBCD Dual-Arm Robot Challenge

Top Prize at the World-Class Robot Competition

DexForce W1 Pro

DexVerse™ Embodied Intelligence Engine

Core Technology

DexForce' s world-class team leads in AI, computer vision, generative 3D, and 3D perception large models. Frontier research drives our DexVerse™, AI, and synthetic data engine to realize general robot intelligence.

Dexterity-BEV: Scaling up Dexterous Manipulation Learning with BEV Alignment

Before generalist policies emerge, heterogeneous robot data are to be unified as the right and
effective representation.

DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks

EmbodiChain

Automated, Efficient, and Modular Platform for Scaling Up Embodied AI Learning

Technological Achievements

Champion of the 1st WBCD Dual-Arm Robot Challenge

IROS Object Pose Estimation: Multiple championships/runner-ups

F-ConvNet/HotSpotNet: Top ranks on KITTI (autonomous driving benchmarks)

DualPoseNet: No.1 accuracy on NOCS (full-DOF pose estimation)

SRDC: Top precision on synthetic-to-real autonomous driving transfer benchmark

IEEE BTAS 2016: 1st in Video Person Recognition Evaluation

Intelligent visual rock-crushing system (Finnish quarries) – efficiency boost

GPNet et al.: deep learning unregistered object grasping + largest simulated dataset

World’s first 3D AffordanceNet: 3D affordance method + benchmark dataset (supports HRI R&D)

SkeletonNet/ToMoNet: first deep learning complex topological surface generation; CVPR 2019 Best Paper Candidate

Analytic Marching (lossless meshing theory/algorithm) – AnalyticMesh open-sourced

Adaptive deep model optimization: bridges MVS & deep reconstruction, enhancing MVS performance

Core Technology

DexForce' s world-class team leads in AI, computer vision, generative 3D, and 3D perception large models. Frontier research drives our DexVerse™, AI, and synthetic data engine to realize general robot intelligence.

Dexterity-BEV: Scaling up Dexterous Manipulation Learning with BEV Alignment

Before generalist policies emerge, heterogeneous robot data are to be unified as the right and effective representation.

DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks

EmbodiChain

Automated, Efficient, and Modular Platform for Scaling Up Embodied AI Learning

Technological Achievements

Champion of the 1st WBCD Dual-Arm Robot Challenge

IROS Object Pose Estimation: Multiple championships/runner-ups

F-ConvNet/HotSpotNet: Top ranks on KITTI (autonomous driving benchmarks)

DualPoseNet: No.1 accuracy on NOCS (full-DOF pose estimation)

SRDC: Top precision on synthetic-to-real autonomous driving transfer benchmark

IEEE BTAS 2016: 1st in Video Person Recognition Evaluation

Intelligent visual rock-crushing system (Finnish quarries) – efficiency boost

GPNet et al.: deep learning unregistered object grasping + largest simulated dataset

World’s first 3D AffordanceNet: 3D affordance method + benchmark dataset (supports HRI R&D)

SkeletonNet/ToMoNet: first deep learning complex topological surface generation; CVPR 2019 Best Paper Candidate

Analytic Marching (lossless meshing theory/algorithm) – AnalyticMesh open-sourced

Adaptive deep model optimization: bridges MVS & deep reconstruction, enhancing MVS performance

Before generalist policies emerge, heterogeneous robot data are to be unified as the right and
effective representation.