Chen Yulin's Blog

Posted 2024-12-31Updated 2026-02-15Notea few seconds read (About 0 words)

One-Shot Visual Imitation Learning via Meta-Learning

#Robotics Research-paper CV ML RobotLearning ImitationLearning

Posted 2024-12-17Updated 2026-02-15Reviewa few seconds read (About 42 words)

Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation

和我的想法非常相近，完成度也很高啊喂。可以参考他的实现思路，引用的文章等等。

#Robotics Scene-graph Research-paper LLM CV Reconstruct 3D-Scene Embodied-AI Semantic Open-Vocabulary

Posted 2024-12-09Updated 2026-02-15Review2 minutes read (About 287 words)

ACDC- Automated Creation of Digital Cousins for Robust Policy Learning

数字孪生(DT)作为现实世界非常精确的映射虽然可以用于高精度的训练但是生产DT资产过于繁琐且没有泛化性，不能做到zero-shot。
数字表亲(DC)通过比对模型特征，从模型库中选择类似的表亲模型，用于重建场景训练机械臂。让机械臂针对不同第一次见的场景具有泛化性。
（a）它减少了手动微调的需要，以保证一定的保真度，从而能够完全自动化地创建数字表亲，（b）它通过提供一组增强的场景来训练机器人策略，从而有助于更好地应对原始场景中的变化。

#Robotics Research-paper LLM CV Reconstruct RobotLearning Real2Sim DT Sim2Real Scene-synthesis

Posted 2024-12-09Updated 2026-02-15Reviewa few seconds read (About 0 words)

Deep Hierarchical Semantic Segmentation

#Research-paper CV Reconstruct Semantic Segmentation Hierarchical

Posted 2024-11-07Updated 2026-02-15Reviewa minute read (About 135 words)

CosyPose-- Consistent multi-view multi-object 6D pose estimation

Estimate accurate 6D poses of multiple known objects in a 3D scene captured by multiple cameras with unknown positions

#Research-paper CV PoseEstimation Multi-view

Posted 2024-08-01Updated 2026-02-15Notea minute read (About 169 words)

自定义 Gen6d 物体

仓库：https://github.com/liuyuan-pal/Gen6D

手册：https://github.com/liuyuan-pal/Gen6D/blob/main/custom_object.md

步骤指令：

python prepare.py --action video2image --input data/custom/part1/ref.mp4 --output data/custom/part1/images --frame_inter 10 --image_size 960  

python prepare.py --action sfm --database_name custom/part1 --colmap D:\COLMAP\COLMAP-3.7-windows-cuda\COLMAP.bat        

# do some cloudcompare thing

python predict.py --cfg configs/gen6d_pretrain.yaml --database custom/part1 --video data/custom/part1/test.mp4 --resolution 460 --output data/custom/part1/test --ffmpeg ffmpeg

ffmpeg -framerate 30 -i %d-bbox.jpg -c:v libx264 -r 30 -pix_fmt yuv420p output.mp4