With the rapid evolution of 3D generation algorithms, the cost of producing 3D humanoid character models has plummeted, yet the field is impeded by the lack of a comprehensive dataset for automatic rigging—a pivotal step in character animation. Addressing this gap, we present HumanRig, the first large-scale dataset specifically designed for 3D humanoid character rigging, encompassing 11,434 meticulously curated T-posed meshes adhered to a uniform skeleton topology. Capitalizing on this dataset, we introduce an innovative, data-driven automatic rigging framework, which overcomes the limitations of GNNbased methods in handling complex AI-generated meshes. Our approach integrates a Prior-Guided Skeleton Estimator (PGSE) module, which uses 2D skeleton joints to provide a preliminary 3D skeleton, and a Mesh-Skeleton Mutual Attention Network (MSMAN) that fuses skeleton features with 3D mesh features extracted by a U-shaped point transformer. This enables a coarse-to-fine 3D skeleton joint regression and a robust skinning estimation, surpassing previous methods in quality and versatility. This work not only remedies the dataset deficiency in rigging research but also propels the animation industry towards more efficient and automated character rigging pipelines.

Neural radiance fields (NeRF) have recently been applied to render large-scale scenes. However, their limited model capacity typically results in blurred rendering results. Existing large-scale NeRFs primarily address this limitation by partitioning the scene into blocks, which are subsequently handled by separate sub-NeRFs. These sub-NeRFs, trained from scratch and processed independently, lead to inconsistencies in geometry and appearance across the scene. Consequently, the rendering quality fails to exhibit significant improvement despite the expansion of model capacity. In this work, we present global-guided focal neural radiance field (GF-NeRF) that achieves high-fidelity rendering of large-scale scenes. Our proposed GF-NeRF utilizes a two-stage (Global and Focal) architecture and a global-guided training strategy. The global stage obtains a continuous representation of the entire scene while the focal stage decomposes the scene into multiple blocks and further processes them with distinct sub-encoders. Leveraging this two-stage architecture, sub-encoders only need fine-tuning based on the global encoder, thus reducing training complexity in the focal stage while maintaining scene-wide consistency. Spatial information and error information from the global stage also benefit the sub-encoders to focus on crucial areas and effectively capture more details of large-scale scenes. No-tably, our approach does not rely on any prior knowledge about the target scene, attributing GF-NeRF adaptable to various large-scale scene types, including street-view and aerial-view scenes. We demonstrate that our method achieves high-fidelity, natural rendering results on various types of large-scale datasets. Our project page: https://shaomq2187.github.io/GF-NeRF/

It is difficult to guarantee an empty living environment to prevent unexpected contact between the object being manipulated by the robot and unplanned obstacles. In this paper, we propose a planar compliant contact control method for planar manipulation to cope with unexpected contact. We first use sheet gel as a multi-dimensional passive elastic element and combine it with a two-finger gripper to design a multi-dimensional elastic gripper. Subsequently, we explore the lumped parameter model for the force-displacement relationship of gel deformation and combine the model with the high impedance motion of robots to design an elastic interaction controller. The controller not only actively adjusts the deformation of the gel to provide the desired contact force and torque depending on contact, but also performs avoidance by following the surface of obstacles. Finally, we design and deploy several planar compliant contact experiments to validate the proposed method and demonstrate the unexpected contact response in human-robot co-packing. The results show that our method enables the robot to remain compliant in the face of unexpected contact caused by unplanned obstacles, which provides a guarantee for safe manipulation. Physics experiments can be viewed in the attached video.

The acquisition of transparent 3D shapes will facilitate many multimedia and computer vision tasks, such as game/movie production and virtual enrioment applications. In this work, we propose a novel method for detailed reconstruction of transparent objects by exploiting polarimetric cues. Most of existing transparent shapes reconstruction methods usually lack sufficient constraints and suffer from the over-smooth problem. Hence, we introduce polarization information as a complementary cue. Specifically, we employ the implicit representation for object's geometry with a neural network, while the polarization render is capable of differentiably rendering the object's polarization images from given illumination configuration. However, direct comparison of rendered polarization images to the real-world captured images will have additional errors due to the transmission in the transparent object. To make the polarimetric cues technically feasible on transparent shapes reconstruction, the concept of reflection percentage which represents proportion of the reflection component is introduced as the weight of the polarization loss. Based on controllable environment setup, we build a polarization dataset containing several solid and smooth transparent objects to verify our method. Experimental results show that our method is capable of recovering detailed shapes and improving reconstruction quality of transparent objects.

This paper presents a learning-based method for transparent surface estimation from a single view polarization image. Existing shape from polarization(SfP) methods have the difficulty in estimating transparent shape since the inherent transmission interference heavily reduces the reliability of physics-based prior. To address this challenge, we propose the concept of physics-based prior confidence, which is inspired by the characteristic that the transmission component in the polarization image has more noise than reflection. The confidence is used to determine the contribution of the interfered physics-based prior. Then, we build a network(TransSfP) with multi-branch architecture to avoid the destruction of relationships between different hierarchical inputs. To train and test our method, we construct a dataset for transparent shape from polarization with paired polarization images and ground-truth normal maps. Extensive experiments and comparisons demonstrate the superior accuracy of our method. Our cdataset and code are publicly available at https://github.com/shaomq2187/TransSfP