Dsvt: Dynamic sparse voxel transformer with rotated sets
Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is
a fundamental problem in 3D perception. Compared with the customized sparse …
a fundamental problem in 3D perception. Compared with the customized sparse …
Cagroup3d: Class-aware grouping for 3d object detection on point clouds
We present a novel two-stage fully sparse convolutional 3D object detection framework,
named CAGroup3D. Our proposed method first generates some high-quality 3D proposals …
named CAGroup3D. Our proposed method first generates some high-quality 3D proposals …
Rbgnet: Ray-based grouping for 3d object detection
As a fundamental problem in computer vision, 3D object detection is experiencing rapid
growth. To extract the point-wise features from the irregularly and sparsely distributed points …
growth. To extract the point-wise features from the irregularly and sparsely distributed points …
Target-driven structured transformer planner for vision-language navigation
Vision-language navigation is the task of directing an embodied agent to navigate in 3D
scenes with natural language instructions. For the agent, inferring the long-term navigation …
scenes with natural language instructions. For the agent, inferring the long-term navigation …
Counterfactual cycle-consistent learning for instruction following and generation in vision-language navigation
Since the rise of vision-language navigation (VLN), great progress has been made in
instruction following--building a follower to navigate environments under the guidance of …
instruction following--building a follower to navigate environments under the guidance of …
A survey of progress on cooperative multi-agent reinforcement learning in open environment
Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and
has made progress in various fields. Specifically, cooperative MARL focuses on training a …
has made progress in various fields. Specifically, cooperative MARL focuses on training a …
Asynchronous multi-agent reinforcement learning for efficient real-time multi-robot cooperative exploration
We consider the problem of cooperative exploration where multiple robots need to
cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement …
cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement …
Towards versatile embodied navigation
With the emergence of varied visual navigation tasks (eg, image-/object-/audio-goal and
vision-language navigation) that specify the target in different ways, the community has …
vision-language navigation) that specify the target in different ways, the community has …
Active perception for visual-language navigation
Visual-language navigation (VLN) is the task of entailing an agent to carry out navigational
instructions inside photo-realistic environments. One of the key challenges in VLN is how to …
instructions inside photo-realistic environments. One of the key challenges in VLN is how to …
Toward Full-Scene Domain Generalization in Multi-Agent Collaborative Bird's Eye View Segmentation for Connected and Autonomous Driving
Collaborative perception has recently gained significant attention in autonomous driving,
improving perception quality by enabling the exchange of additional information among …
improving perception quality by enabling the exchange of additional information among …