NVS-HO: A Benchmark for Novel View Synthesis of Handheld Objects
This work addresses the challenge of novel view synthesis for hand-held objects in real-world scenes using only RGB inputs. It introduces the first benchmark specifically designed for this task, comprising hand-held object sequences for training and checkerboard-based calibration sequences that provide ground-truth camera poses for evaluation. To tackle the problem, the authors estimate camera poses by combining Structure-from-Motion (SfM) with a pre-trained VGG network and develop a synthesis model that integrates Neural Radiance Fields (NeRF) with 3D Gaussian splatting. Experimental results demonstrate that existing methods suffer significant performance degradation under the non-rigid, unconstrained conditions typical of hand-held objects, thereby highlighting the critical role of this benchmark in advancing robust novel view synthesis research.