Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing time. In this paper, we present EfficientNeRF as an efficient NeRF-based method to represent 3D scene and synthesize novel-view images. Although several ways exist to accelerate the training or testing process, it is still difficult to much reduce time for both phases simultaneously. We analyze the density and weight distribution of the sampled points then propose valid and pivotal sampling at the coarse and fine stage, respectively, to significantly improve sampling efficiency. In addition, we design a novel data structure to cache the whole scene during testing to accelerate the rendering speed. Overall, our method can reduce over 88\% of training time, reach rendering speed of over 200 FPS, while still achieving competitive accuracy. Experiments prove that our method promotes the practicality of NeRF in the real world and enables many applications.
Spherical robot is a nonlinear, nonholonomic and unstable system which increases the difficulty of the direction and trajectory tracking problem. In this study, we propose a new direction controller HTSMC, an instruction planning controller MPC, and a trajectory tracking framework MHH. The HTSMC is designed by integrating a fast terminal algorithm, a hierarchical method, the motion features of a spherical robot, and its dynamics. In addition, the new direction controller has an excellent control effect with a quick response speed and strong stability. MPC can obtain optimal commands that are then transmitted to the velocity and direction controller. Since the two torque controllers in MHH are all Lyapunov-based sliding mode controllers, the MHH framework may achieve optimal control performance while assuring stability. Finally, the two controllers eliminate the requirement for MPC's stability and dynamic constraints. Finally, hardware experiments demonstrate the efficacy of the HTSMC, MPC, and MHH.
Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decoder for triplet prediction, or utilize two parallel decoders to detect individual objects and interactions separately, and compose triplets by a matching process. In contrast, we decouple the triplet prediction into human-object pair detection and interaction classification. Our main motivation is that detecting the human-object instances and classifying interactions accurately needs to learn representations that focus on different regions. To this end, we present Disentangled Transformer, where both encoder and decoder are disentangled to facilitate learning of two sub-tasks. To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder. Extensive experiments show that our method outperforms prior work on two public HOI benchmarks by a sizeable margin. Code will be available.
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We propose MixFormer to find a solution. First, we combine local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields. Second, we propose bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions. These two designs are integrated to achieve efficient feature mixing among windows and dimensions. Our MixFormer provides competitive results on image classification with EfficientNet and shows better results than RegNet and Swin Transformer. Performance in downstream tasks outperforms its alternatives by significant margins with less computational costs in 5 dense prediction tasks on MS COCO, ADE20k, and LVIS. Code is available at \url{https://github.com/PaddlePaddle/PaddleClas}.
We propose a novel neural rendering pipeline, Hybrid Volumetric-Textural Rendering (HVTR), which synthesizes virtual human avatars from arbitrary poses efficiently and at high quality. First, we learn to encode articulated human motions on a dense UV manifold of the human body surface. To handle complicated motions (e.g., self-occlusions), we then leverage the encoded information on the UV manifold to construct a 3D volumetric representation based on a dynamic pose-conditioned neural radiance field. While this allows us to represent 3D geometry with changing topology, volumetric rendering is computationally heavy. Hence we employ only a rough volumetric representation using a pose-conditioned downsampled neural radiance field (PD-NeRF), which we can render efficiently at low resolutions. In addition, we learn 2D textural features that are fused with rendered volumetric features in image space. The key advantage of our approach is that we can then convert the fused features into a high resolution, high-quality avatar by a fast GAN-based textural renderer. We demonstrate that hybrid rendering enables HVTR to handle complicated motions, render high-quality avatars under user-controlled poses/shapes and even loose clothing, and most importantly, be fast at inference time. Our experimental results also demonstrate state-of-the-art quantitative results.
Gaze object prediction (GOP) is a newly proposed task that aims to discover the objects being stared at by humans. It is of great application significance but still lacks a unified solution framework. An intuitive solution is to incorporate an object detection branch into an existing gaze prediction method. However, previous gaze prediction methods usually use two different networks to extract features from scene image and head image, which would lead to heavy network architecture and prevent each branch from joint optimization. In this paper, we build a novel framework named GaTector to tackle the gaze object prediction problem in a unified way. Particularly, a specific-general-specific (SGS) feature extractor is firstly proposed to utilize a shared backbone to extract general features for both scene and head images. To better consider the specificity of inputs and tasks, SGS introduces two input-specific blocks before the shared backbone and three task-specific blocks after the shared backbone. Specifically, a novel defocus layer is designed to generate object-specific features for object detection task without losing information or requiring extra computations. Moreover, the energy aggregation loss is introduced to guide the gaze heatmap to concentrate on the stared box. In the end, we propose a novel mDAP metric that can reveal the difference between boxes even when they share no overlapping area. Extensive experiments on the GOO dataset verify the superiority of our method in all three tracks, i.e. object detection, gaze estimation, and gaze object prediction.
We present EgoRenderer, a system for rendering full-body neural avatars of a person captured by a wearable, egocentric fisheye camera that is mounted on a cap or a VR headset. Our system renders photorealistic novel views of the actor and her motion from arbitrary virtual camera locations. Rendering full-body avatars from such egocentric images come with unique challenges due to the top-down view and large distortions. We tackle these challenges by decomposing the rendering process into several steps, including texture synthesis, pose construction, and neural image translation. For texture synthesis, we propose Ego-DPNet, a neural network that infers dense correspondences between the input fisheye images and an underlying parametric body model, and to extract textures from egocentric inputs. In addition, to encode dynamic appearances, our approach also learns an implicit texture stack that captures detailed appearance variation across poses and viewpoints. For correct pose generation, we first estimate body pose from the egocentric view using a parametric model. We then synthesize an external free-viewpoint pose image by projecting the parametric model to the user-specified target viewpoint. We next combine the target pose image and the textures into a combined feature image, which is transformed into the output color image using a neural image translation network. Experimental evaluations show that EgoRenderer is capable of generating realistic free-viewpoint avatars of a person wearing an egocentric camera. Comparisons to several baselines demonstrate the advantages of our approach.
Generating photo-realistic images from a text description is a challenging problem in computer vision. Previous works have shown promising performance to generate synthetic images conditional on text by Generative Adversarial Networks (GANs). In this paper, we focus on the category-consistent and relativistic diverse constraints to optimize the diversity of synthetic images. Based on those constraints, a category-consistent and relativistic diverse conditional GAN (CRD-CGAN) is proposed to synthesize $K$ photo-realistic images simultaneously. We use the attention loss and diversity loss to improve the sensitivity of the GAN to word attention and noises. Then, we employ the relativistic conditional loss to estimate the probability of relatively real or fake for synthetic images, which can improve the performance of basic conditional loss. Finally, we introduce a category-consistent loss to alleviate the over-category issues between K synthetic images. We evaluate our approach using the Birds-200-2011, Oxford-102 flower and MSCOCO 2014 datasets, and the extensive experiments demonstrate superiority of the proposed method in comparison with state-of-the-art methods in terms of photorealistic and diversity of the generated synthetic images.
In conditional Generative Adversarial Networks (cGANs), when two different initial noises are concatenated with the same conditional information, the distance between their outputs is relatively smaller, which makes minor modes likely to collapse into large modes. To prevent this happen, we proposed a hierarchical mode exploring method to alleviate mode collapse in cGANs by introducing a diversity measurement into the objective function as the regularization term. We also introduced the Expected Ratios of Expansion (ERE) into the regularization term, by minimizing the sum of differences between the real change of distance and ERE, we can control the diversity of generated images w.r.t specific-level features. We validated the proposed algorithm on four conditional image synthesis tasks including categorical generation, paired and un-paired image translation and text-to-image generation. Both qualitative and quantitative results show that the proposed method is effective in alleviating the mode collapse problem in cGANs, and can control the diversity of output images w.r.t specific-level features.
Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the training-inference discrepancy problem, i.e., exposure bias, where association error could accumulate in the inference and make the trajectories drift. In this paper, we propose a novel method for optimizing tracklet consistency, which directly takes the prediction errors into account by introducing an online, end-to-end tracklet search training process. Notably, our methods directly optimize the whole tracklet score instead of pairwise affinity. With sequence model as appearance encoders of tracklet, our tracker achieves remarkable performance gain from conventional tracklet association baseline. Our methods have also achieved state-of-the-art in MOT15~17 challenge benchmarks using public detection and online settings.