diff --git a/.DS_Store b/.DS_Store new file mode 100644 index 0000000..b13e04e Binary files /dev/null and b/.DS_Store differ diff --git a/README.md b/README.md index 885a589..214b58c 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,7 @@ VinAI Research, Vietnam > **Abstract**: Instance segmentation on 3D point clouds (3DIS) is a longstanding challenge in computer vision, where state-of-the-art methods are mainly based on full supervision. As annotating ground truth dense instance masks is tedious and expensive, solving 3DIS with weak supervision has become more practical. In this paper, we propose GaPro, a new instance segmentation for 3D point clouds using axis-aligned 3D bounding box supervision. Our two-step approach involves generating pseudo labels from box annotations and training a 3DIS network with the resulting labels. Additionally, we employ the self-training strategy to improve the performance of our method further. We devise an effective Gaussian Process to generate pseudo instance masks from the bounding boxes and resolve ambiguities when they overlap, resulting in pseudo instance masks with their uncertainty values. Our experiments show that GaPro outperforms previous weakly supervised 3D instance segmentation methods and has competitive performance compared to state-of-the-art fully supervised ones. Furthermore, we demonstrate the robustness of our approach, where we can adapt various state-of-the-art fully supervised methods to the weak supervision task by using our pseudo labels for training. -![overview](docs/gapro_arch.png) +![overview](docs/gapro_arch.jpg) Details of the model architecture and experimental results can be found in [our paper](https://arxiv.org/abs/2307.13251): diff --git a/docs/.DS_Store b/docs/.DS_Store new file mode 100644 index 0000000..131d1a0 Binary files /dev/null and b/docs/.DS_Store differ diff --git a/docs/gapro_arch.jpg b/docs/gapro_arch.jpg new file mode 100644 index 0000000..de2a172 Binary files /dev/null and b/docs/gapro_arch.jpg differ diff --git a/docs/gapro_arch.png b/docs/gapro_arch.png deleted file mode 100644 index 45f07dd..0000000 Binary files a/docs/gapro_arch.png and /dev/null differ