“…Although NeRF provides an alternative solution for 3D reconstruction compared to traditional photogrammetry methods and can produce promising results in situations where photogrammetry may fail to deliver accurate results, it still faces several limitations, as reported by different authors [63][64][65][66][67][68]. Some of the main issues from a 3D metrological perspective that need to be considered include:…”
Section: Nerf-based Methodsmentioning
confidence: 99%
“…Tancik et al [69] and Sitzmann et al [70] adopted the position encoding operation with a different frequency to NeRFs in order to improve the resolution of the neural rendering outcome since high-frequency representation capacity in NeRFs is insufficient. Following this, other approaches have focused on improving the efficiency and resolution of the neural rendering outcome in different ways, including model acceleration [20,71], compression [72][73][74], relighting [75][76][77], and View-Dependence Normalization [78] (Zhu et al, 2023), or high-resolution 2D feature planes [68]. Müller et al [20] introduced the concept of instant Neural Graphics Primitives with a Multiresolution Hash Encoding, which allows for fast and efficient generation of 3D models.…”
This paper presents a critical analysis of image-based 3D reconstruction using neural radiance fields (NeRFs), with a focus on quantitative comparisons with respect to traditional photogrammetry. The aim is, therefore, to objectively evaluate the strengths and weaknesses of NeRFs and provide insights into their applicability to different real-life scenarios, from small objects to heritage and industrial scenes. After a comprehensive overview of photogrammetry and NeRF methods, highlighting their respective advantages and disadvantages, various NeRF methods are compared using diverse objects with varying sizes and surface characteristics, including texture-less, metallic, translucent, and transparent surfaces. We evaluated the quality of the resulting 3D reconstructions using multiple criteria, such as noise level, geometric accuracy, and the number of required images (i.e., image baselines). The results show that NeRFs exhibit superior performance over photogrammetry in terms of non-collaborative objects with texture-less, reflective, and refractive surfaces. Conversely, photogrammetry outperforms NeRFs in cases where the object’s surface possesses cooperative texture. Such complementarity should be further exploited in future works.
“…Although NeRF provides an alternative solution for 3D reconstruction compared to traditional photogrammetry methods and can produce promising results in situations where photogrammetry may fail to deliver accurate results, it still faces several limitations, as reported by different authors [63][64][65][66][67][68]. Some of the main issues from a 3D metrological perspective that need to be considered include:…”
Section: Nerf-based Methodsmentioning
confidence: 99%
“…Tancik et al [69] and Sitzmann et al [70] adopted the position encoding operation with a different frequency to NeRFs in order to improve the resolution of the neural rendering outcome since high-frequency representation capacity in NeRFs is insufficient. Following this, other approaches have focused on improving the efficiency and resolution of the neural rendering outcome in different ways, including model acceleration [20,71], compression [72][73][74], relighting [75][76][77], and View-Dependence Normalization [78] (Zhu et al, 2023), or high-resolution 2D feature planes [68]. Müller et al [20] introduced the concept of instant Neural Graphics Primitives with a Multiresolution Hash Encoding, which allows for fast and efficient generation of 3D models.…”
This paper presents a critical analysis of image-based 3D reconstruction using neural radiance fields (NeRFs), with a focus on quantitative comparisons with respect to traditional photogrammetry. The aim is, therefore, to objectively evaluate the strengths and weaknesses of NeRFs and provide insights into their applicability to different real-life scenarios, from small objects to heritage and industrial scenes. After a comprehensive overview of photogrammetry and NeRF methods, highlighting their respective advantages and disadvantages, various NeRF methods are compared using diverse objects with varying sizes and surface characteristics, including texture-less, metallic, translucent, and transparent surfaces. We evaluated the quality of the resulting 3D reconstructions using multiple criteria, such as noise level, geometric accuracy, and the number of required images (i.e., image baselines). The results show that NeRFs exhibit superior performance over photogrammetry in terms of non-collaborative objects with texture-less, reflective, and refractive surfaces. Conversely, photogrammetry outperforms NeRFs in cases where the object’s surface possesses cooperative texture. Such complementarity should be further exploited in future works.
“…NeRF is a powerful technique for novel view synthesis, but they face several challenges in different scenarios. Many works have extended NeRFs to handle dynamic (Pumarola et al 2021;Liu et al 2023), unbounded (Zhang et al 2020;Barron et al 2022;Reiser et al 2023), and large-scale scenes (Tancik et al 2022;Turki, Ramanan, and Satyanarayanan 2022), as well as to optimize NeRFs from in-the-wild (Martin-Brualla et al 2021) and dark images (Mildenhall et al 2022). Some works have also improved the generalization (Yu et al 2021b;Wang et al 2021c; Chen and Lee 2023), bundle sampling (Kurz et al 2022), initialization (Bergman, Kellnhofer, and Wetzstein 2021;Tancik et al 2021) and data structure (Yu et al 2021a;Müller et al 2022) of NeRFs.…”
Neural Radiance Fields (NeRF) have shown promise in generating realistic novel views from sparse scene images. However, existing NeRF approaches often encounter challenges due to the lack of explicit 3D supervision and imprecise camera poses, resulting in suboptimal outcomes. To tackle these issues, we propose AltNeRF---a novel framework designed to create resilient NeRF representations using self-supervised monocular depth estimation (SMDE) from monocular videos, without relying on known camera poses. SMDE in AltNeRF masterfully learns depth and pose priors to regulate NeRF training. The depth prior enriches NeRF's capacity for precise scene geometry depiction, while the pose prior provides a robust starting point for subsequent pose refinement. Moreover, we introduce an alternating algorithm that harmoniously melds NeRF outputs into SMDE through a consistence-driven mechanism, thus enhancing the integrity of depth priors. This alternation empowers AltNeRF to progressively refine NeRF representations, yielding the synthesis of realistic novel views. Extensive experiments showcase the compelling capabilities of AltNeRF in generating high-fidelity and robust novel views that closely resemble reality.
“…Alternatively, discrete voxel grids can be used [Clark 2022;Müller et al 2022a;Sun et al 2021]. Rendering can be fast [Esposito et al 2022;Li et al 2022a;Lin et al 2022;Reiser et al 2023] to even work on mobile devices [Cao et al 2023]. While real-time reconstruction is significantly more difficult, careful optimization and camera parameter refinement permits fast capture and view synthesis [Clark 2022;Haitz et al 2023;Jiang et al 2023;Müller et al 2022b;Rosinol et al 2022].…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.