This paper proposes a knowledge distillation method for foreground object search (FoS). Given a background and a rectangle specifying the foreground location and scale, FoS retrieves compatible foregrounds in a certain category for later image composition. Foregrounds within the same category can be grouped into a small number of patterns. Instances within each pattern are compatible with \textit{any} query input interchangeably. These instances are referred to as \textit{interchangeable foregrounds}. We first present a pipeline to build pattern-level FoS dataset containing labels of interchangeable foregrounds. We then establish a benchmark dataset for further training and testing following the pipeline. As for the proposed method, we first train a foreground encoder to learn representations of interchangeable foregrounds. We then train a query encoder to learn query-foreground compatibility following a knowledge distillation framework. It aims to transfer knowledge from interchangeable foregrounds to supervise representation learning of compatibility. The query feature representation is projected to the same latent space as interchangeable foregrounds, enabling very efficient and interpretable instance-level search. Furthermore, pattern-level search is feasible to retrieve more controllable, reasonable and diverse foregrounds. The proposed method outperforms the previous state-of-the-art by $10.42\%$ in absolute difference and $24.06\%$ in relative improvement evaluated by mean average precision (mAP). Extensive experimental results also demonstrate its efficacy from various aspects. The benchmark dataset and code will be release shortly.
Previous methods on estimating detailed human depth often require supervised training with `ground truth' depth data. This paper presents a self-supervised method that can be trained on YouTube videos without known depth, which makes training data collection simple and improves the generalization of the learned network. The self-supervised learning is achieved by minimizing a photo-consistency loss, which is evaluated between a video frame and its neighboring frames warped according to the estimated depth and the 3D non-rigid motion of the human body. To solve this non-rigid motion, we first estimate a rough SMPL model at each video frame and compute the non-rigid body motion accordingly, which enables self-supervised learning on estimating the shape details. Experiments demonstrate that our method enjoys better generalization and performs much better on data in the wild.
We study the energy minimization problem in low-level vision tasks from a novel perspective. We replace the heuristic regularization term with a learnable subspace constraint, and preserve the data term to exploit domain knowledge derived from the first principle of a task. This learning subspace minimization (LSM) framework unifies the network structures and the parameters for many low-level vision tasks, which allows us to train a single network for multiple tasks simultaneously with completely shared parameters, and even generalizes the trained network to an unseen task as long as its data term can be formulated. We demonstrate our LSM framework on four low-level tasks including interactive image segmentation, video segmentation, stereo matching, and optical flow, and validate the network on various datasets. The experiments show that the proposed LSM generates state-of-the-art results with smaller model size, faster training convergence, and real-time inference.
In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-view pooling module to attentively fuse convolutional features across views. Extensive experiments on existing 3D registration benchmarks show that our method outperforms existing local descriptors both quantitatively and qualitatively.
Convolutional Neural Networks (CNNs) are typically constructed by stacking multiple building blocks, each of which contains a normalization layer such as batch normalization (BN) and a rectified linear function such as ReLU. However, this work shows that the combination of normalization and rectified linear function leads to inhibited channels, which have small magnitude and contribute little to the learned feature representation, impeding the generalization ability of CNNs. Unlike prior arts that simply removed the inhibited channels, we propose to "wake them up" during training by designing a novel neural building block, termed Channel Equilibrium (CE) block, which enables channels at the same layer to contribute equally to the learned representation. We show that CE is able to prevent inhibited channels both empirically and theoretically. CE has several appealing benefits. (1) It can be integrated into many advanced CNN architectures such as ResNet and MobileNet, outperforming their original networks. (2) CE has an interesting connection with the Nash Equilibrium, a well-known solution of a non-cooperative game. (3) Extensive experiments show that CE achieves state-of-the-art performance on various challenging benchmarks such as ImageNet and COCO.
This paper studies a new problem, namely active lighting recurrence (ALR) that physically relocalizes a light source to reproduce the lighting condition from single reference image for a same scene, which may suffer from fine-grained changes during twice observations. ALR is of great importance for fine-grained visual inspection and change detection, because some phenomena or minute changes can only be clearly observed under particular lighting conditions. Therefore, effective ALR should be able to online navigate a light source toward the target pose, which is challenging due to the complexity and diversity of real-world lighting and imaging processes. To this end, we propose to use the simple parallel lighting as an analogy model and based on Lambertian law to compose an instant navigation ball for this purpose. We theoretically prove the feasibility, i.e., equivalence and convergence, of this ALR approach for realistic near point light source and small near surface light source. Besides, we also theoretically prove the invariance of our ALR approach to the ambiguity of normal and lighting decomposition. The effectiveness and superiority of the proposed approach have been verified by both extensive quantitative experiments and challenging real-world tasks on fine-grained change detection of cultural heritages. We also validate the generality of our approach to non-Lambertian scenes.
We present a method to capture both 3D shape and spatially varying reflectance with a multi-view photometric stereo (MVPS) technique that works for general isotropic materials. Our algorithm is suitable for perspective cameras and nearby point light sources. Our data capture setup is simple, which consists of only a digital camera, some LED lights, and an optional automatic turntable. From a single viewpoint, we use a set of photometric stereo images to identify surface points with the same distance to the camera. We collect this information from multiple viewpoints and combine it with structure-from-motion to obtain a precise reconstruction of the complete 3D shape. The spatially varying isotropic bidirectional reflectance distribution function (BRDF) is captured by simultaneously inferring a set of basis BRDFs and their mixing weights at each surface point. In experiments, we demonstrate our algorithm with two different setups: a studio setup for highest precision and a desktop setup for best usability. According to our experiments, under the studio setting, the captured shapes are accurate to 0.5 millimeters and the captured reflectance has a relative root-mean-square error (RMSE) of 9%. We also quantitatively evaluate state-of-the-art MVPS on a newly collected benchmark dataset, which is publicly available for inspiring future research.
The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity. These methods are limited when high-resolution outputs are needed since the memory and time costs grow cubically as the volume resolution increases. In this paper, we propose a both memory and time efficient cost volume formulation that is complementary to existing multi-view stereo and stereo matching approaches based on 3D cost volumes. First, the proposed cost volume is built upon a standard feature pyramid encoding geometry and context at gradually finer scales. Then, we can narrow the depth (or disparity) range of each stage by the depth (or disparity) map from the previous stage. With gradually higher cost volume resolution and adaptive adjustment of depth (or disparity) intervals, the output is recovered in a coarser to fine manner. We apply the cascade cost volume to the representative MVS-Net, and obtain a 23.1% improvement on DTU benchmark (1st place), with 50.6% and 74.2% reduction in GPU memory and run-time. It is also the state-of-the-art learning-based method on Tanks and Temples benchmark. The statistics of accuracy, run-time and GPU memory on other representative stereo CNNs also validate the effectiveness of our proposed method.
We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos online, which exhibit large illumination variations that make them suitable for training of reflectance separation and can facilitate object-level decomposition. The main contribution of our approach is a proposed image representation based on local color distributions that allows training to be insensitive to the local misalignments of multi-view images. In addition, we present a new guidance cue for unsupervised training that exploits synergy between highlight separation and intrinsic image decomposition. Over a broad range of objects, our technique is shown to yield state-of-the-art results for both of these tasks.
This paper presents a neural network to estimate a detailed depth map of the foreground human in a single RGB image. The result captures geometry details such as cloth wrinkles, which are important in visualization applications. To achieve this goal, we separate the depth map into a smooth base shape and a residual detail shape and design a network with two branches to regress them respectively. We design a training strategy to ensure both base and detail shapes can be faithfully learned by the corresponding network branches. Furthermore, we introduce a novel network layer to fuse a rough depth map and surface normals to further improve the final result. Quantitative comparison with fused `ground truth' captured by real depth cameras and qualitative examples on unconstrained Internet images demonstrate the strength of the proposed method.