WE3.L4.5
MS-RAFT-3D: A Multi-Scale Architecture for Recurrent Image-based Scene Flow
Jakob Schmid, Azin Jahedi, Noah Berenguel Senn, Andrés Bruhn, University of Stuttgart, Germany
Session:
WE3.L4: Three-Dimensional Image and Video Analysis and Processing 2 Lecture
Track:
[IV-3D] Three-dimensional image and video analysis and processing
Location:
Dena'ina: Kahtnu 2
Presentation Time:
Wed, 17 Sep, 11:00 - 11:15 Anchorage Time (UTC -8)
Session Chair:
Rabab Ward, University of British Columbia
Session WE3.L4
WE3.L4.1: SPARSE2DGS: SPARSE-VIEW SURFACE RECONSTRUCTION USING 2D GAUSSIAN SPLATTING WITH DENSE POINT CLOUD
Natsuki Takama, Shintaro Ito, Koichi Ito, Tohoku University, Japan; Hwann-Tzong Chen, National Tsing Hua University, Taiwan; Takafumi Aoki, Tohoku University, Japan
WE3.L4.2: MAMBA-BASED GLOBAL CORRELATION LEARNING FOR LIGHT FIELD SPATIAL SUPER-RESOLUTION
Bo Peng, Ruoxi Li, Jianjun Lei, Zhe Zhang, Tianjin University, China
WE3.L4.3: SWINSCALE-LFVS: PARALLEL FEATURE INTEGRATION FOR LIGHT FIELD VIEW SYNTHESIS
Muhammad Zubair, Paulo Nunes, Caroline Conti, Luís Ducla Soares, Instituto de Telecomunicações, Instituto Universitário de Lisboa (ISCTE-IUL), Portugal
WE3.L4.4: EQUR: Equivariant Uncertainty Quantification and Refinement for Point Cloud Registration
Adam Misik, Siemens AG/Technical University Munich, Germany; Driton Salihu, Xiaoang Zhang, Technical University Munich, Germany; Heike Brock, Siemens AG, Germany; Eckehard Steinbach, Technical University Munich, Germany
WE3.L4.5: MS-RAFT-3D: A Multi-Scale Architecture for Recurrent Image-based Scene Flow
Jakob Schmid, Azin Jahedi, Noah Berenguel Senn, Andrés Bruhn, University of Stuttgart, Germany
WE3.L4.6: DISENEMO: LEARNING DISENTANGLED EMOTIONAL REPRESENTATION FROM FACIAL MOTION FOR 3D TALKING HEAD GENERATION
Ziang Chen, Tianhua Qi, Cheng Lu, Wenming Zheng, Southeast University, China
Contacts