Foreword to the Special Section on 3D Object Retrieval 2022 Symposium (3DOR2022)

The aim of the 3D Object Retrieval (3DOR) series is to provide a premier venue for research in 3D / 4D visual content search, exploration and understanding for researchers from diverse fields such as Computer Vision, Computer Graphics, Machine Learning, Cognitive Science and Human-Computer Interaction. In addition, the Shape Retrieval Contest (SHREC) is an established venue for benchmarking new and existing methods in shape retrieval. SHREC and 3DOR have been running together since 2009, with SHREC being the benchmarking arm of 3DOR and 3DOR being the dissemination and networking arm of SHREC. 3DOR 2022 was the 15th edition in the 3DOR series, organized this year as a symposium, which better reflects its contents. It took place on the 1st and 2nd of September 2022 in Florence, Italy. In order to allow attendance of researchers who might have traveling restrictions due to COVID-19, the symposium was handled as a hybrid event, with both in-presence and remote presentations and participants. As introduced in 2020, accepted full papers were published in the Elsevier Computers & Graphics (C&G) journal. To this end, the full paper submission track followed a two-stage review process. A second call for submissions of short papers took place and a selection of these papers was published in the Eurographics Digital Library, which hosts all the 3DOR proceedings. The symposium programme featured 16 presentations. We were pleased to have Professor Emanuele Rodolà, “La Sapienza” University of Rome, as Keynote Speaker who gave an inspiring talk on “From sound to metric priors: A new paradigm for shape generation”. 16 papers were submitted to the full paper track, out of which 12 were accepted for publication in Computers & Graphics. Of these 12 papers, 6 were research papers and 6 were the outcome of SHREC tracks. Moreover, new from this edition, a “Best Paper” was chosen among full paper presentations. The award was given to [1] based on both the outcomes of the reviewing process, the quality of the paper and presentation. The committee was composed by Silvia Biasotti, Claudio Ferrari, and Remco C. Veltkamp. Research full papers (6). Full papers presented different studies, ranging from multimodal registration of 3D objects [2], dense segmentation of 3D object parts with a specific application to cars [3], enanchement of manually drawn CAD model sketches [4], to new benchmark datasets [5] or new deep learning solutions for improving the representation of meshes [1] and semantic segmentation [6]. SHREC full papers (6). SHREC papers presented at 3DOR addressed very different problems as well. Dataset and benchmarking challenges were proposed to push the research frontiers on topics such as the detection of human gestures [7], pothole and road cracks detection [8], reconstruction and fitting of geometric primitives [9], open-set [10] and sketch-based 3D object retrieval [11], or protein-ligand binding site detection [12]. All the papers presented preliminary results of challenges related to the proposed benchmarks. An important asset of 3DOR is the valued IPC members whom we would sincerely like to thank for their reviewing, which was crucial to create a high-quality program. We also thank University of Florence for hosting the event, the Eurographics Association and Stephanie Behnke in particular for their continued support and Joaquim Jorge, editor-in-chief of C&G, for making this C&G Special Section possible.