https://github.com/3dlg-hcvc/M3DRef-CLIP
공식 코드Multi3DRefer: Grounding Text Description to Multiple 3D Objects
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Visual Navigation is the problem of navigating an agent, e.g. a mobile robot, in an environment using camera input only. The agent is given a target image (an image it will see from the target position), and its goal is to move from its current position to the target by applying a sequence of actions, based on the camera observations only.
Source: Vision-based Navigation Using Deep Reinforcement Learning
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Multi3DRefer: Grounding Text Description to Multiple 3D Objects
Towards Autonomous Crop-Agnostic Visual Navigation in Arable Fields
Addressing the challenges of loop detection in agricultural environments
Fanoos: Multi-Resolution, Multi-Strength, Interactive Explanations for Learned Systems
Fanoos: Multi-Resolution, Multi-Strength, Interactive Explanations for Learned Systems
LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences
Using Constraints to Discover Sparse and Alternative Subgroup Descriptions
S$^*$: A Heuristic Information-Based Approximation Framework for Multi-Goal Path Finding
Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation
BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps
LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning
The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes
Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph
LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models
Discriminative Particle Filter Reinforcement Learning for Complex Partial Observations
Flipping the switch on local exploration: Genetic Algorithms with Reversals
CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
Simultaneous Navigation and Construction Benchmarking Environments
Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments
POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.