48th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC2026)
Novel view synthesis (NVS) is an active researchtopic in computer vision, owing to the success of neural radiance field (NeRF) and 3D Gaussian splatting (3DGS) methods. While NVS opens the door to potential applications in gastroendoscopy, such as extending the field of view of endoscopic images and enabling digital twins for 3D archiving and endoscopist manipulation training, the dataset is insufficient to evaluate NVS for gastroendoscopy. In this paper, we present the first real gastroscopy dataset for NVS, namely the GastroNVS dataset, which contains a set of gastroscopic images, camera poses, and a point cloud for real gastroendoscopy inspection. To assess the suitability of the GastroNVS dataset, we evaluate several 3DGS methods and discuss the challenges for future development.
The GastroNVS dataset contains gastroendoscopic image sequences along with their estimated camera poses and the reconstructed 3D point cloud by SfM. The dataset was collected during real gastroendoscopy inspections, which capture the gastric surfaces of real patients with gastric lesions and include relatively large viewpoint changes that occurred in the real inspections. Thus, it provides an evaluation platform for real environments in gastroendoscopy.
