DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

ArXi:2604.13416v1 Announce Type: cross Advances in radiance fields have enabled photorealistic novel view synthesis. In several domains, large-scale real-world datasets have been developed to comprehensive benchmarking and to facilitate progress beyond scene-specific reconstruction. However, for distractor-free radiance fields, a large-scale dataset with clean and cluttered images per scene remains lacking, limiting the development. To address this gap, we