RESUMEN
Neural radiance fields (NeRF) have demonstrated impressive performance in novel view synthesis, but are still slow to render complex scenes at a high resolution. We introduce a novel method to boost the NeRF rendering speed by utilizing the temporal coherence between consecutive frames. Rather than computing features of each frame entirely from scratch, we reuse the coherent information (e.g., density and color) computed from the previous frames to help render the current frame, which significantly boosts rendering speed. To effectively manage the coherent information of previous frames, we introduce a history buffer with a multiple-plane structure, which is built online and updated from old frames to new frames. We name this buffer as multiple plane buffer (MPB). With this MPB, a new frame can be efficiently rendered using the warped features from previous frames. Extensive experiments on the NeRF-Synthetic, LLFF, and Mip-NeRF-360 datasets demonstrate that our method significantly boosts rendering efficiency and achieves 4× speedup on real-world scenes compared to the baseline methods while preserving competitive rendering quality.
RESUMEN
We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. The difficulty of reliably capturing geometric context in existing methods impedes their ability to accurately enforce the consistency between the different geometric properties, thereby leading to a bottleneck of geometric estimation quality. We therefore propose the Adaptive Surface Normal (ASN) constraint, a simple yet efficient method. Our approach extracts geometric context that encodes the geometric variations present in the input image and correlates depth estimation with geometric constraints. By dynamically determining reliable local geometry from randomly sampled candidates, we establish a surface normal constraint, where the validity of these candidates is evaluated using the geometric context. Furthermore, our normal estimation leverages the geometric context to prioritize regions that exhibit significant geometric variations, which makes the predicted normals accurately capture intricate and detailed geometric information. Through the integration of geometric context, our method unifies depth and surface normal estimations within a cohesive framework, which enables the generation of high-quality 3D geometry from images. We validate the superiority of our approach over state-of-the-art methods through extensive evaluations and comparisons on diverse indoor and outdoor datasets, showcasing its efficiency and robustness. Code and data are available at https://github.com/xxlong0/ASNDepth.
RESUMEN
Bone marrow (BM) mesenchymal stem cells (MSCs) are cells capable of expanding and differentiating in vitro into nonhematopoietic cells. Neurotrophic cytokines, such as human epidermal growth factor (hEGF) and bovine fibroblast growth factor (bFGF) can induce differentiation into neural cells (NCs). When BM MSCs were cultured with hEGF and bFGF, RNA expression of neuronal specific markers Nestin, MAP-2, and tyrosine hydroxylase (TH) were observed. We tested a new cytokine combination to generate mature NCs. The plastic-adherent cells were collected and then split when they were 90% confluent from an enriched mononuclear cell layer. At passage 3, MSCs were cultured in neural differentiation media (dbcAMP, IBMX, FGF-8, BDNF, hEGF, and bFGF in NEUROBASAL media plus B27). Cells were counted on day 6. Immunofluorescent staining and reverse transcriptase (RT)-PCR were performed to evaluate the expression of neural markers. On day 6, 66% of cells developed dendrites and presented typical neural cell morphology. Some cells were positive for early neural markers Nestin and beta-tubulin III. Cells expressing mature neuronal markers (NF, NeuN, Tau, Nurr1, GABA, oligodendryte GalC, and glial GFAP) were also seen. By adding hEGF, bFGF, dbcAMP, IBMX, BDNF, and bFGF-8 into NEUROBASAL media plus B27, BM MSCs were directed toward becoming early and mature NCs.
