3D Semantic Segmentation is a computer vision task that involves the partitioning of a three-dimensional (3D) point cloud or voxel grid into different segments or regions, with each segment assigned a semantic label that represents the category or class of the objects or surfaces within that segment. This task extends the concept of semantic segmentation from two-dimensional (2D) images to 3D space and is particularly important for understanding and interpreting the 3D environment in applications such as robotics, autonomous driving, augmented reality, and urban planning.

Posts

MM TTA: Multi Modal Test Time Adaptation for 3D Semantic Segmentation

MM TTA: Multi Modal Test Time Adaptation for 3D Semantic Segmentation Test time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and explore a new multi modal extension of test time adaptation for 3D semantic segmentation. We find that directly applying existing methods usually results in performance instability at test time because multi modal input is not considered jointly. To design a framework that can take full advantage of multi modality, where each modality provides regularized self supervisory signals to other modalities, we propose two complementary modules within and across the modalities. First, Intra modal Pseudolabel Generation (Intra PG) is introduced to obtain reliable pseudo labels within each modality by aggregating information from two models that are both pre trained on source data but updated with target data at different paces. Second, Inter modal Pseudo label Refinement (Inter PR) adaptively selects more reliable pseudo labels from different modalities based on a proposed consistency scheme. Experiments demonstrate that our regularized pseudo labels produce stable self learning signals in numerous multi modal test time adaptation scenarios for 3D semantic segmentation. Visit our project website at https://www.nec labs.com/˜mas/MM TTA