Palladium-Catalyzed Weak Chelation-Assisted Site-Selective C-H Arylation of N-Aryl Pyridones via 2-fold C-H Activation.

Palladium-catalyzed weak chelation-assisted oxidative cross-dehydrogenative coupling of arenes has been accomplished. The use of medicinally important pyridones as the intrinsic directing group, regioselectivity, 2-fold C-H activation, and late-stage modification of bioactive compounds are the important practical features.

Biorelevant Weakly Coordinating Directing Group Assisted C-H Alkenylation with Cyclopropanols via Sequential C-H/C-C Activation.

A weakly coordinating biorelevant intrinsic directing group (DG) assisted site-selective C-H alkenylation via sequential C-H/C-C bond activation has been accomplished under Ru(II)-catalysis using readily accessible cyclopropyl alcohol as an alkenyl surrogate. Utilization of an intrinsic DG, exclusive regioselectivity, functional group diversity, late-stage natural product and drug mutations are the important practical features.

A redox-neutral weak carbonyl chelation assisted C4-H allylation of indoles with vinylcyclopropanes.

A weak acyl chelation-assisted distal C4-H allylation of indoles has been accomplished using vinylcyclopropanes as an allylating agent under redox-neutral ruthenium(II) catalysis. The regioselectivity, removable directing group, substrate scope and diastereoselectivity are the important practical features.

C3I-SynFace: A synthetic head pose and facial depth dataset using seed virtual human models.

This article presents C3I-SynFace: a large-scale synthetic human face dataset with corresponding ground truth annotations of head pose and face depth generated using the iClone 7 Character Creator "Realistic Human 100" toolkit with variations in ethnicity, gender, race, age, and clothing. The data is generated from 15 female and 15 male synthetic 3D human models extracted from iClone software in FBX format. Five facial expressions - neutral, angry, sad, happy, and scared are added to the face models to add further variations. With the help of these models, an open-source data generation pipeline in Python is proposed to import these models into the 3D computer graphics tool Blender and render the facial images along with the ground truth annotations of head pose and face depth in raw format. The datasets contain more than 100k ground truth samples with their annotations. With the help of virtual human models, the proposed framework can generate extensive synthetic facial datasets (e.g., head pose or face depths datasets) with a high degree of control over facial and environmental variations such as pose, illumination, and background. Such large datasets can be used for the improved and targeted training of deep neural networks.

3D face-model reconstruction from a single image: A feature aggregation approach using hierarchical transformer with weak supervision.

Convolutional Neural Networks (CNN) have gained popularity as the de-facto model for any computer vision task. However, CNN have drawbacks, i.e. they fail to extract long-range perceptions in images. Due to their ability to capture long-range dependencies, transformer networks are adopted in computer vision applications, where they show state-of-the-art (SOTA) results in popular tasks like image classification, instance segmentation, and object detection. Although they gained ample attention, transformers have not been applied to 3D face reconstruction tasks. In this work, we propose a novel hierarchical transformer model, added to a feature pyramid aggregation structure, to extract the 3D face parameters from a single 2D image. More specifically, we use pre-trained Swin Transformer backbone networks in a hierarchical manner and add the feature fusion module to aggregate the features in multiple stages. We use a semi-supervised training approach and train our model in a supervised way with the 3DMM parameters from a publicly available dataset and unsupervised training with a differential renderer on other parameters like facial keypoints and facial features. We also train our network on a hybrid unsupervised loss and compare the results with other SOTA approaches. When evaluated across two public datasets on face reconstruction and dense 3D face alignment tasks, our method can achieve comparable results to the current SOTA performance and in some instances do better than the SOTA methods. A detailed subjective evaluation also shows that our method performs better than the previous works in realism and occlusion resistance.

Weak Chelation-Assisted C4-Selective Alkylation of Indoles with Cyclopropanols via Sequential C-H/C-C Bond Activation.

A Rh-catalyzed weak chelation-guided C4-alkylation of indoles has been accomplished using cyclopropanols as an alkylating agent via the cascade C-H and C-C bond activation. The substrate scope, functional group tolerance, and late-stage mutation of drug molecules are the important practical features.

Palladium-Catalyzed 2-fold C-H Activation/C-C Coupling for C4-Arylation of Indoles Using Weak Chelation.

Palladium-catalyzed weak chelation-assisted regioselective C4-arylation of indoles has been accomplished using a readily available arene at moderate temperature. The C4-arylation, weak chelating benzoyl (Bz) directing group, cross-dehydrogenative coupling (CDC), broad substrate scope, and late-stage diversifications are the important practical features.

An efficient encoder-decoder model for portrait depth estimation from single images trained on pixel-accurate synthetic data.

Depth estimation from a single image frame is a fundamental challenge in computer vision, with many applications such as augmented reality, action recognition, image understanding, and autonomous driving. Large and diverse training sets are required for accurate depth estimation from a single image frame. Due to challenges in obtaining dense ground-truth depth, a new 3D pipeline of 100 synthetic virtual human models is presented to generate multiple 2D facial images and corresponding ground truth depth data, allowing complete control over image variations. To validate the synthetic facial depth data, we propose an evaluation of state-of-the-art depth estimation algorithms based on single image frames on the generated synthetic dataset. Furthermore, an improved encoder-decoder based neural network is presented. This network is computationally efficient and shows better performance than current state-of-the-art when tested and evaluated across 4 public datasets. Our training methodology relies on the use of synthetic data samples which provides a more reliable ground truth for depth estimation. Additionally, using a combination of appropriate loss functions leads to improved performance than the current state-of-the-art network performances. Our approach clearly outperforms competing methods across different test datasets, setting a new state-of-the-art for facial depth estimation from synthetic data.