CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoors Object Detection from Multi-view Images
This work improves 3D object detection for indoor scenes, which is incremental as it builds on existing reconstruction and detection networks.
The paper tackles 3D indoor object detection from multi-view images by addressing ambiguity in image-to-3D correspondence without explicit geometry, achieving state-of-the-art performance with mAP@0.25 and mAP@0.5 on ScanNet and ARKitScenes datasets.
This paper introduces CN-RMA, a novel approach for 3D indoor object detection from multi-view images. We observe the key challenge as the ambiguity of image and 3D correspondence without explicit geometry to provide occlusion information. To address this issue, CN-RMA leverages the synergy of 3D reconstruction networks and 3D object detection networks, where the reconstruction network provides a rough Truncated Signed Distance Function (TSDF) and guides image features to vote to 3D space correctly in an end-to-end manner. Specifically, we associate weights to sampled points of each ray through ray marching, representing the contribution of a pixel in an image to corresponding 3D locations. Such weights are determined by the predicted signed distances so that image features vote only to regions near the reconstructed surface. Our method achieves state-of-the-art performance in 3D object detection from multi-view images, as measured by mAP@0.25 and mAP@0.5 on the ScanNet and ARKitScenes datasets. The code and models are released at https://github.com/SerCharles/CN-RMA.