Single Diffusion Model Research Articles

AvatarStudio: Text-Driven Editing of 3D Dynamic Human Head Avatars

Capturing and editing full-head performances enables the creation of virtual characters with various applications such as extended reality and media production. The past few years witnessed a steep rise in the photorealism of human head avatars. Such avatars can be controlled through different input data modalities, including RGB, audio, depth, IMUs, and others. While these data modalities provide effective means of control, they mostly focus on editing the head movements such as the facial expressions, head pose, and/or camera viewpoint. In this paper, we propose AvatarStudio, a text-based method for editing the appearance of a dynamic full head avatar. Our approach builds on existing work to capture dynamic performances of human heads using Neural Radiance Field (NeRF) and edits this representation with a text-to-image diffusion model. Specifically, we introduce an optimization strategy for incorporating multiple keyframes representing different camera viewpoints and time stamps of a video performance into a single diffusion model. Using this personalized diffusion model, we edit the dynamic NeRF by introducing view-and-time-aware Score Distillation Sampling (VT-SDS) following a model-based guidance approach. Our method edits the full head in a canonical space and then propagates these edits to the remaining time steps via a pre-trained deformation network. We evaluate our method visually and numerically via a user study, and results show that our method outperforms existing approaches. Our experiments validate the design choices of our method and highlight that our edits are genuine, personalized, as well as 3D- and time-consistent.

Correction: Diffusion weighted imaging in patients with rectal cancer: Comparison between Gaussian and non-Gaussian models

[This corrects the article DOI: 10.1371/journal.pone.0184197.].

Palladium sorption on glutaraldehyde-crosslinked chitosan

The high nitrogen content of chitosan is the main reason for its ability to sorb metal ions through several mechanisms including ion-exchange or chelation, depending on the metal and the pH of the solution. Glutaraldehyde is used to crosslink chitosan through imine linkage between amine groups of chitosan and aldehyde groups of the crosslinking agent. This modified biosorbent was studied for palladium recovery in acidic medium (around pH 2). The influence of several parameters such as pH and competitor anions were studied with respect to sorption equilibrium. Sorption isotherms were obtained and modeled using the Langmuir and the Freundlich model. This study also examines the effect of palladium concentration, particle size, sorbent dosage, and the extent of crosslinking on sorption kinetics. Kinetic curves are modeled using single diffusion model equations to evaluate the predominance of either external or intraparticle mass transfer resistance. The influence of the acid used to control the pH of the solution was examined in conjunction with the influence of competitor anions. Sulfuric acid proves to be unfavorable to palladium sorption, in comparison with hydrochloric acid. However, the addition of chloride anions in a palladium solution, whose pH is controlled with sulfuric acid, enhances metal anion sorption: results are interpreted with reference to chloropalladate speciation.

Frequency response diffusion of propane in silicalite-1

The frequency response spectra of propane in silicalite-1 were measured at equilibrium pressures of 0.5–8.0 Torr and temperatures of 303–363 K and analysed by non-isothermal diffusion, two independent diffusion processes, and single-diffusion models. The first model is physically feasible for the explanation of the bimodal FR behaviour of this system, but the heat effect can be eliminated by reducing the coverage in the zeolite. Compared with propane, the bimodal form of the frequency response curves of p-xylene in silicalite-1 is attributed to two diffusion processes occurring separately in the sinusoidal and straight channels of the sorbent. The intracrystalline self-diffusion coefficient of propane in silicalite-1 determined in the present work is of the order of 10 −9 m 2 s −1 and decreases with increasing concentration of the adsorbate in the zeolite. This result is consistent with PFG NMR and previous FR studies.