ECCV 2020 Papers

Non-local self-similarity and sparsity principles have proven to be powerful priors for natural image modeling. We propose a novel differentiable relaxation of joint sparsity that exploits both principles and leads to a general framework for image restoration which is (1) trainable end to end, (2) fully interpretable, and (3) much more compact than competing deep learning architectures. We apply this approach to denoising, jpeg deblocking, and demosaicking, and show that, with as few as 100K parameters, its performance on several standard benchmarks is on par or better than state-of-the-art methods that may have an order of magnitude or more parameters."

We present a novel method of CNN inference for pixel processor array (PPA) vision sensors, designed to take advantage of their massive parallelism and analog compute capabilities. PPA sensors consist of an array of processing elements (PEs), with each PE capable of light capture, data storage and computation, allowing various computer vision processing to be executed directly upon the sensor device. The key idea behind our approach is storing network weights ""in-pixel"" within the PEs of the PPA sensor itself to allow various computations, such as multiple different image convolutions, to be carried out in parallel. Our approach can perform convolutional layers, max pooling, ReLu, and a final fully connected layer entirely upon the PPA sensor, while leaving no untapped computational resources. This is in contrast to previous works that only use a sensor-level processing to sequentially compute image convolutions, and must transfer data to an external digital processor to complete the computation. We demonstrate our approach on the SCAMP-5 vision system, performing inference of a MNIST digit classification network at over 3000 frames per second and over 93% classification accuracy. This is the first work demonstrating CNN inference conducted entirely upon the processor array of a PPA vision sensor device, requiring no external processing."

Continuous sign language recognition (SLR) is a challenging task that requires learning on both spatial and temporal dimensions of signing frame sequences. Most recent work accomplishes this by using CNN and RNN hybrid networks. However, training these networks is generally non-trivial, and most of them fail in learning unseen sequence patterns, causing an unsatisfactory performance for online recognition. In this paper, we propose a fully convolutional network (FCN) for online SLR to concurrently learn spatial and temporal features from weakly annotated video sequences with only sentence-level annotations given. A gloss feature enhancement (GFE) module is introduced in the proposed network to enforce better sequence alignment learning. The proposed network is end-to-end trainable without any pre-training. We conduct experiments on two large scale SLR datasets. Experiments show that our method for continuous SLR is effective and performs well in online recognition."

This paper presents a road detection technique based on long-wave infrared (LWIR) polarization imaging for autonomous navigation regardless of illumination conditions, day and night. Division of Focal Plane (DoFP) imaging technology enables acquisition of infrared polarization images in real time using a monocular camera. Zero-distribution prior embodies the zero-distribution of Angle of Polarization (AoP) of a road scene image, which provides a significant contrast between the road and the background. This paper combines zero-distribution of AoP, the difference of Degree of linear Polarization (DoP), and the edge information to segment the road region in the scene. We developed a LWIR DoFP Dataset of Road Scene (LDDRS) consisting of 2,113 annotated images. Experiment results on the LDDRS dataset demonstrate the merits of the proposed road detection method based on the zero-distribution prior. The LDDRS dataset is available at https://github.com/polwork/LDDRS"

There has been great progress in human 3D mesh recovery and great interest in learning about the world from consumer video data. Unfortunately current methods for 3D human mesh recovery work rather poorly on consumer video data, since on the Internet, unusual camera viewpoints and aggressive truncations are the norm rather than a rarity. We study this problem and make a number of contributions to address it: (i) we propose a simple but highly effective self-training framework that adapts human 3D mesh recovery systems to consumer videos and demonstrate its application to two recent systems; (ii) we introduce evaluation protocols and keypoint annotations for 13K frames across four consumer video datasets for studying this task, including evaluations on out-of-image keypoints; and (iii) we show that our method substantially improves PCK and human-subject judgments compared to baselines, both on test videos from the dataset it was trained on, as well as on three other datasets without further adaptation."

The requirement for paired shadow and shadow-free images limits the size and diversity of shadow removal datasets and hinders the possibility of training large-scale, robust shadow removal algorithms. We propose a shadow removal method that can be trained using only shadow and non-shadow patches cropped from the shadow images themselves. Our method is trained via an adversarial framework, following a physical model of shadow formation. Our central contribution is a set of physics-based constraints that enables this adversarial training. Our method achieves competitive shadow removal results compared to state-of-the-art methods that are trained with fully paired shadow and shadow-free images. The advantages of our training regime are even more pronounced in shadow removal for videos. Our method can be fine-tuned on a testing video with only the shadow masks generated by a pre-trained shadow detector and outperforms state-of-the-art methods on this challenging test. We illustrate the advantages of our method on our proposed video shadow removal dataset. "

We propose and validate two end-to-end deep learning architectures to learn foot pressure distribution maps (dynamics) from 2D or 3D human pose (kinematics). The networks are trained using 1.36 million synchronized pose+pressure data pairs from 10 subjects performing multiple takes of a 5-minute long choreographed Taiji sequence. Using leave-one-subject-out cross validation, we demonstrate reliable and repeatable foot pressure prediction, setting the first baseline for solving a non-obvious pose to pressure cross-modality mapping problem in computer vision. Furthermore, we compute and quantitatively validate Center of Pressure (CoP) and Base of Support (BoS), two key components for stability analysis, from the predicted foot pressure distributions."

A 3D imaging and mapping system that can handle both multiple-viewers and dynamic-objects is attractive for many applications. We propose a freeform structured light system that does not rigidly constrain camera(s) to the projector. By introducing an optimized phase-coded aperture in the projector, we transform the projector pattern to encode depth in its defocus robustly; this allows a camera to estimate depth, in projector coordinates, using local information. Additionally, we project a Kronecker-multiplexed pattern that provides global context to establish correspondence between camera and projector pixels. Together with aperture coding and projected pattern, the projector offers a unique 3D labeling for every location of the scene. The projected pattern can be observed in part or full by any camera, to reconstruct both the 3D map of the scene and the camera pose in the projector coordinates. This system is optimized using a fully differentiable rendering model and a CNN-based reconstruction. We build a prototype and demonstrate high-quality 3D reconstruction with an unconstrained camera, for both dynamic scenes and multi-camera systems."

We present a method for novel view synthesis from input images that are freely distributed around a scene. Our method does not rely on a regular arrangement of input views, can synthesize images for free camera movement through the scene, and works for general scenes with unconstrained geometric layouts. We calibrate the input images via SfM and erect a coarse geometric scaffold via MVS. This scaffold is used to create a proxy depth map for a novel view of the scene. Based on this depth map, a recurrent encoder-decoder network processes reprojected features from nearby views and synthesizes the new view. Our network does not need to be optimized for a given scene. After training on a dataset, it works in previously unseen environments with no fine-tuning or per-scene optimization. We evaluate the presented approach on challenging real-world datasets, including Tanks and Temples, where we demonstrate successful view synthesis for the first time and substantially outperform prior and concurrent work."

We present a ForkGAN for task-agnostic image translation that can boost multiple vision tasks in adverse weather conditions. Three tasks of image localization/retrieval, semantic image segmentation, and object detection are evaluated. The key challenge is achieving high-quality image translation without any explicit supervision, or task awareness. Our innovation is a fork-shape generator with one encoder and two decoders that disentangles the domain-specific and domain-invariant information. We force the cyclic translation between the weather conditions to go through a common encoding space, and make sure the encoding features reveal no information about the domains. Experimental results show our algorithm produces state-of-the-art image synthesis results and boost three vision tasks' performances in adverse weathers."

We describe a procedure for removing dependency on a cohort of training data from a trained deep network that improves upon and generalizes previous methods to different readout functions, and can be extended to ensure forgetting in the final activations of the network. We introduce a new bound on how much information can be extracted per query about the forgotten cohort from a black-box network for which only the input-output behavior is observed. The proposed forgetting procedure has a deterministic part derived from the differential equations of a linearized version of the model, and a stochastic part that ensures information destruction by adding noise tailored to the geometry of the loss landscape. We exploit the connections between the final activations and weight dynamics of a DNN inspired by Neural Tangent Kernels to compute the information in the final activations."

We address the challenging task of anticipating human-object interaction in first person videos. Most existing methods either ignore how the camera wearer interacts with objects, or simply considers body motion as a separate modality. In contrast, we observe that the intentional hand movement reveals critical information about the future activity. Motivated by this observation, we adopt intentional hand movement as a feature representation, and propose a novel deep network that jointly models and predicts the egocentric hand motion, interaction hotspots and future action. Specifically, we consider the future hand motion as the motor attention, and model this attention using probabilistic variables in our deep model. The predicted motor attention is further used to select the discriminative spatial-temporal visual features for predicting actions and interaction hotspots. We present extensive experiments demonstrating the benefit of the proposed joint model. Importantly, our model produces new state-of-the-art results for action anticipation on both EGTEA Gaze+ and the EPIC-Kitchens datasets. Our project page is available at https://aptx4869lm.github.io/ForecastingHOI/"

In this paper, we introduce Foley Music, a system that can synthesize plausible music for a silent video clip about people playing musical instruments. We first identify two key intermediate representations for a successful video to music generator: body keypoints from videos and MIDI events from audio recordings. We then formulate music generation from videos as a motion-to-midi translation problem. We present a Graph-Transformer framework that can accurately predict MIDI event sequences in accordance with the body movements; The MIDI event can then be converted to realistic music using an off-the-shelf music synthesizer tool. We demonstrate the effectiveness of our models on videos containing a variety of music performances. Experimental results show that our model outperforms several existing systems in generating music that is pleasant to listen to. More importantly, the MIDI representations are fully interpretable and transparent, thus enabling us to perform music editing flexibly. We encourage the readers to watch the supplementary video with audio turned on to experience the results. "

We present a new flow-based video completion algorithm. Previous flow completion methods are often unable to retain the sharpness of motion boundaries. Our method first extracts and completes motion edges, and then uses them to guide piecewise-smooth flow completion with sharp edges. Existing methods propagate colors among local flow connections between adjacent frames. However, not all missing regions in a video can be reached in this way because the motion boundaries form impenetrable barriers. Our method alleviates this problem by introducing non-local flow connections to temporally distant frames, enabling propagating video content over motion boundaries. We validate our approach on the DAVIS dataset. Both visual and quantitative results show that our method compares favorably against the state-of-the-art algorithms."

Deep neural networks are generally considered black-box models that offer less interpretability for their decision process. To address this limitation, Class Activation Map (CAM) provides an attractive solution that visualizes class-specific discriminative regions in an input image. The remarkable ability of CAMs to locate class discriminating regions has been exploited in weakly-supervised segmentation and localization tasks. In this work, we explore a new direction towards the possible use of CAM in deep network learning process. We note that such visualizations lend insights into the workings of deep CNNs and could be leveraged to introduce additional constraints during the learning stage. Specifically, the CAMs for negative classes (negative CAMs) often have false activations even though those classes are absent from an image. Thereby, we propose a loss function that seeks to minimize peaks within the negative CAMs, called Homogeneous Negative CAM loss. This way, in an effort to fix localization errors, our loss provides an extra supervisory signal that helps the model to better discriminate between similar classes. Our designed loss function is easy to implement and can be readily integrated into existing DNNs. We evaluate it on a number of classification tasks including large-scale recognition, multi-label classification and fine-grained recognition. Our loss provides better performance compared to other loss functions across the studied tasks. Additionally, we show that the proposed loss function provides higher robustness against adversarial attacks and noisy labels. "

Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works mainly tackle this problem by focusing on how to locate the most discriminative parts, more complementary parts, and parts of various granularities. However, less effort has been placed to which granularities are the most discriminative and how to fuse information cross multi-granularity. In this work, we propose a novel framework for fine-grained visual classification to tackle these problems. In particular, we propose: (i) a novel progressive training strategy that adds new layers in each training step to exploit information based on the smaller granularity information found at the last step and the previous stage. (ii) a simple jigsaw puzzle generator to form images contain information of different granularity levels. We obtain state-of-the-art performances on several standard FGVC benchmark datasets, where the proposed method consistently outperforms existing methods or delivers competitive results. Code is provided as part of supplementary material, and will be publicly released upon acceptance."

Massive semantically labeled datasets are readily available for 2D images, however, are much harder to achieve for 3D scenes. Objects in 3D repositories like ShapeNet are labeled, but regrettably only in isolation, so without context. 3D scenes can be acquired by range scanners on city-level scale, but much fewer with semantic labels. Addressing this disparity, we introduce a new optimization procedure, which allows training for 3D detection with raw 3D scans while using as little as 5\,\% of the object labels and still achieve comparable performance. Our optimization uses two networks. A scene network maps an entire 3D scene to a set of 3D object centers. As we assume the scene not to be labeled by centers, no classic loss, such as Chamfer can be used to train it. Instead, we use another network to emulate the loss. This loss network is trained on a small labeled subset and maps a non-centered 3D object in the presence of distractions to its own center. This function is very similar -- and hence can be used instead of -- the gradient the supervised loss would provide. Our evaluation documents competitive fidelity at a much lower level of supervision, respectively higher quality at comparable supervision. Supplementary material can be found at: https://dgriffiths3.github.io."

We propose a novel method for neural network quantization that casts the neural architecture search problem as one of hyperparameter search to find non-uniform bit distributions throughout the layers of a CNN. We perform the search assuming a Multi-Task Gaussian Processes prior, which splits the problem to multiple tasks, each corresponding to different number of training epochs, and explore the space by sampling those configurations that yield maximum information. We then show that with significantly lower precision in the last layers we achieve a minimal loss of accuracy with appreciable memory savings. We test our findings on the CIFAR10 and ImageNet datasets using the VGG, ResNet and GoogLeNet architectures."

Change Captioning is a task that aims to describe the difference between images with natural language. Most existing methods treat this problem as a difference judgment without the existence of distractors such as viewpoint changes. However, in practice, viewpoint changes happen often and can overwhelm the semantic difference to be described. In this paper, we propose a novel visual encoder to explicitly distinguish viewpoint changes from semantic changes in the change captioning task. Moreover, we further simulate the attention preference of humans and propose a novel reinforcement learning process to fine-tune the attention directly with the language evaluation rewards. Extensive experimental results show that our method outperforms the state-of-the-art approaches by a large margin in both Spot-the-Diff and CLEVR-Change datasets."