Stylizing 3D Scene via Implicit Representation and HyperNetwork

StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning

“…6, we compare our results with [5], a pioneering work introducing NeRF into stylization. [5] calculates the style and content losses on small sub-sampled patches which approximate large patches. However, such approximation degrades the preservation of content details, as shown in our comparisons.…”

“…As is shown in framed yellow boxes, the fine-level shapes like the Figure 6. Qualitative comparisons to Chiang et al [5]. We compare the stylized results on Tanks and Temples dataset [24].…”

“…In Fig. 6, we compare our results with [5], a pioneering work introducing NeRF into stylization. [5] calculates the style and content losses on small sub-sampled patches which approximate large patches.…”

StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions

“…Cao et al [4] stylize indoor scenes using a point cloud representation that cannot be directly used to texture a mesh. Other methods combine novel view synthesis and NST for consistent stylization from only a few input images [8,25,35]. In contrast, we do not require a network during inference to produce stylization results; our results can be rendered directly by a standard graphics pipeline.…”

“…This is difficult since style transfer losses are typically defined on 2D image features [21], so NST does not immediately generalize to 3D meshes. Recently, style transfer has been combined with novel view synthesis to stylize arbitrary scenes with a neural renderer from a sparse set of input images [8,25,35]. These model-based methods require a forward pass during inference and cannot directly be applied to meshes.…”