Tiong, Leslie Ching Ow Sigmund, Dick Teoh, Andrew Beng Jin 2024-01-12T02:47:51Z 2024-01-12T02:47:51Z 2023-06-29 2022-12 0302-9743 https://pubs.kist.re.kr/handle/201004/76518 Recently, the transformer model has been successfully employed for the multi-view 3D reconstruction problem. However, challenges remain in designing an attention mechanism to explore the multi-view features and exploit their relations for reinforcing the encoding-decoding modules. This paper proposes a new model, namely 3D coarse-to-fine transformer (3D-C2FT), by introducing a novel coarse-to-fine (C2F) attention mechanism for encoding multi-view features and rectifying defective voxel-based 3D objects. C2F attention mechanism enables the model to learn multi-view information flow and synthesize 3D surface correction in a coarse to fine-grained manner. The proposed model is evaluated by ShapeNet and Multi-view Real-life voxel-based datasets. Experimental results show that 3D-C2FT achieves notable results and outperforms several competing models on these datasets. English SPRINGER INTERNATIONAL PUBLISHING AG 3D-C2FT: Coarse-to-Fine Transformer for Multi-view 3D Reconstruction Conference 10.1007/978-3-031-26319-4_13 1 16th Asian Conference on Computer Vision (ACCV), pp.211 - 227 16th Asian Conference on Computer Vision (ACCV) 211 227 SZ Macao, PEOPLES R CHINA 2022-12-04 COMPUTER VISION - ACCV 2022, PT I 001000819500013 2-s2.0-85151055806