AI RESEARCH
AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments
arXiv CS.CV
•
ArXi:2603.25494v1 Announce Type: new Indoor monocular semantic scene completion (MSSC) is notably challenging than its outdoor counterpart due to complex spatial layouts and severe occlusions. While transformers are well suited for modeling global dependencies, their high memory cost and difficulty in reconstructing fine-grained details have limited their use in indoor MSSC. To address these limitations, we