Rakesh Ranjan, Wei Ye, Avinash Paliwal, Jinhui Xiong, Nima Kalantari, Xilong Zhou
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
DNGaussian Ground Truth Stage 2 (Repair + Inpaint) -Ours FSGS CoR-GS Stage 1 (Repair) Figure 1. We introduce a novel sparse view synthesis method that employs two diffusion models, "repair" and "inpainting", which are responsible for aiding in the reconstruction of visible regions and hallucinating missing regions, respectively. Our approach involves a two-stage optimization process. In the first stage, we use the repair model to constrain the 3DGS optimization and reconstruct the regions covered by the input images. As shown, the output of the first stage properly reconstructs the visible areas, but contains missing regions, which are marked in white. In the second stage, we utilize the inpainting model to fill in these missing areas and continue optimization using the repair model to seamlessly integrate the hallucinated regions with the rest of the scene. Here, we compare our method ("Stage 2") against several state-of-the-art techniques on a 360°scene using only three input images.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2503.10860")
get_code_for_paper("2503.10860")
have("2503.10860")
Connect an agent — have() is free.