Text2Control3D: Controllable 3D Avatar Generation in Neural Radiance Fields using Geometry-Guided Text-to-Image Diffusion Model

Recent advances in diffusion models such as ControlNet have enabled geometrically controllable, high-fidelity text-to-image generation. However, none of them addresses the question of adding such controllability to text-to-3D generation. In response, we propose Text2Control3D, a controllable text-to-3D avatar generation method whose facial expression is controllable given a monocular video casually captured with hand-held camera. Our main strategy is to construct the 3D avatar in Neural Radiance Fields (NeRF) optimized with a set of controlled viewpoint-aware images that we generate from ControlNet, whose condition input is the depth map extracted from the input video. When generating the viewpoint-aware images, we utilize cross-reference attention to inject well-controlled, referential facial expression and appearance via cross attention. We also conduct low-pass filtering of Gaussian latent of the diffusion model in order to ameliorate the viewpoint-agnostic texture problem we observed from our empirical analysis, where the viewpoint-aware images contain identical textures on identical pixel positions that are incomprehensible in 3D. Finally, to train NeRF with the images that are viewpoint-aware yet are not strictly consistent in geometry, our approach considers per-image geometric variation as a view of deformation from a shared 3D canonical space. Consequently, we construct the 3D avatar in a canonical space of deformable NeRF by learning a set of per-image deformation via deformation field table. We demonstrate the empirical results and discuss the effectiveness of our method.

FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields

As recent advances in Neural Radiance Fields (NeRF) have enabled high-fidelity 3D face reconstruction and novel view synthesis, its manipulation also became an essential task in 3D vision. However, existing manipulation methods require extensive human labor, such as a user-provided semantic mask and manual attribute search unsuitable for non-expert users. Instead, our approach is designed to require a single text to manipulate a face reconstructed with NeRF. To do so, we first train a scene manipulator, a latent code-conditional deformable NeRF, over a dynamic scene to control a face deformation using the latent code. However, representing a scene deformation with a single latent code is unfavorable for compositing local deformations observed in different instances. As so, our proposed Position-conditional Anchor Compositor (PAC) learns to represent a manipulated scene with spatially varying latent codes. Their renderings with the scene manipulator are then optimized to yield high cosine similarity to a target text in CLIP embedding space for text-driven manipulation. To the best of our knowledge, our approach is the first to address the text-driven manipulation of a face reconstructed with NeRF. Extensive results, comparisons, and ablation studies demonstrate the effectiveness of our approach.

Local 3D Editing via 3D Distillation of CLIP Knowledge

3D content manipulation is an important computer vision task with many real-world applications (e.g., product design, cartoon generation, and 3D Avatar editing). Recently proposed 3D GANs can generate diverse photorealistic 3D-aware contents using Neural Radiance fields (NeRF). However, manipulation of NeRF still remains a challenging problem since the visual quality tends to degrade after manipulation and suboptimal control handles such as 2D semantic maps are used for manipulations. While text-guided manipulations have shown potential in 3D editing, such approaches often lack locality. To overcome these problems, we propose Local Editing NeRF (LENeRF), which only requires text inputs for fine-grained and localized manipulation. Specifically, we present three add-on modules of LENeRF, the Latent Residual Mapper, the Attention Field Network, and the Deformation Network, which are jointly used for local manipulations of 3D features by estimating a 3D attention field. The 3D attention field is learned in an unsupervised way, by distilling the zero-shot mask generation capability of CLIP to the 3D space with multi-view guidance. We conduct diverse experiments and thorough evaluations both quantitatively and qualitatively.

Low-level Pose Control of Tilting Multirotor for Wall Perching Tasks Using Reinforcement Learning

Recently, needs for unmanned aerial vehicles (UAVs) that are attachable to the wall have been highlighted. As one of the ways to address the need, researches on various tilting multirotors that can increase maneuverability has been employed. Unfortunately, existing studies on the tilting multirotors require considerable amounts of prior information on the complex dynamic model. Meanwhile, reinforcement learning on quadrotors has been studied to mitigate this issue. Yet, these are only been applied to standard quadrotors, whose systems are less complex than those of tilting multirotors. In this paper, a novel reinforcement learning-based method is proposed to control a tilting multirotor on real-world applications, which is the first attempt to apply reinforcement learning to a tilting multirotor. To do so, we propose a novel reward function for a neural network model that takes power efficiency into account. The model is initially trained over a simulated environment and then fine-tuned using real-world data in order to overcome the sim-to-real gap issue. Furthermore, a novel, efficient state representation with respect to the goal frame that helps the network learn optimal policy better is proposed. As verified on real-world experiments, our proposed method shows robust controllability by overcoming the complex dynamics of tilting multirotors.

Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network

Training a Convolutional Neural Network (CNN) to be robust against rotation has mostly been done with data augmentation. In this paper, another progressive vision of research direction is highlighted to encourage less dependence on data augmentation by achieving structural rotational invariance of a network. The deep equivariance-bridged SO(2) invariant network is proposed to echo such vision. First, Self-Weighted Nearest Neighbors Graph Convolutional Network (SWN-GCN) is proposed to implement Graph Convolutional Network (GCN) on the graph representation of an image to acquire rotationally equivariant representation, as GCN is more suitable for constructing deeper network than spectral graph convolution-based approaches. Then, invariant representation is eventually obtained with Global Average Pooling (GAP), a permutation-invariant operation suitable for aggregating high-dimensional representations, over the equivariant set of vertices retrieved from SWN-GCN. Our method achieves the state-of-the-art image classification performance on rotated MNIST and CIFAR-10 images, where the models are trained with a non-augmented dataset only. Quantitative validations over invariance of the representations also demonstrate strong invariance of deep representations of SWN-GCN over rotations.

ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building

Scan data of urban environments often include representations of dynamic objects, such as vehicles, pedestrians, and so forth. However, when it comes to constructing a 3D point cloud map with sequential accumulations of the scan data, the dynamic objects often leave unwanted traces in the map. These traces of dynamic objects act as obstacles and thus impede mobile vehicles from achieving good localization and navigation performances. To tackle the problem, this paper presents a novel static map building method called ERASOR, Egocentric RAtio of pSeudo Occupancy-based dynamic object Removal, which is fast and robust to motion ambiguity. Our approach directs its attention to the nature of most dynamic objects in urban environments being inevitably in contact with the ground. Accordingly, we propose the novel concept called pseudo occupancy to express the occupancy of unit space and then discriminate spaces of varying occupancy. Finally, Region-wise Ground Plane Fitting (R-GPF) is adopted to distinguish static points from dynamic points within the candidate bins that potentially contain dynamic points. As experimentally verified on SemanticKITTI, our proposed method yields promising performance against state-of-the-art methods overcoming the limitations of existing ray tracing-based and visibility-based methods.