MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction

Multiple cameras can provide multi-view video coverage of a person. It is necessary to fuse multi-view data, e.g., for subsequent behavioral analysis, while such fusion often relies on calibration of cameras in traditional solutions. However, it is non-trivial to calibrate multiple cameras. In this work, we propose a method to reconstruct 3D human body from multiple uncalibrated camera views. First, we adopt a pre-trained human body encoder to process each individual camera view, such that human body models and parameters can be reconstructed for each view. Next, instead of simply averaging models across views, we train a network to determine the weights of individual views for their fusion, based on the parameters estimated for joints and hands of human body as well as camera positions. Further, we turn to the mesh surface of human body for dynamic fusion, such that facial expression can be seamlessly integrated into the model of human body. Our method has demonstrated superior performance in reconstructing human body upon two public datasets. More importantly, our method can flexibly support ad-hoc deployment of an arbitrary number of cameras, which has significant potential in related applications. We will release source code upon acceptance of the paper.

DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration

Blind face restoration usually synthesizes degraded low-quality data with a pre-defined degradation model for training, while more complex cases could happen in the real world. This gap between the assumed and actual degradation hurts the restoration performance where artifacts are often observed in the output. However, it is expensive and infeasible to include every type of degradation to cover real-world cases in the training data. To tackle this robustness issue, we propose Diffusion-based Robust Degradation Remover (DR2) to first transform the degraded image to a coarse but degradation-invariant prediction, then employ an enhancement module to restore the coarse prediction to a high-quality image. By leveraging a well-performing denoising diffusion probabilistic model, our DR2 diffuses input images to a noisy status where various types of degradation give way to Gaussian noise, and then captures semantic information through iterative denoising steps. As a result, DR2 is robust against common degradation (e.g. blur, resize, noise and compression) and compatible with different designs of enhancement modules. Experiments in various settings show that our framework outperforms state-of-the-art methods on heavily degraded synthetic and real-world datasets.

Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots

Accurate 3D object detection in LiDAR based point clouds suffers from the challenges of data sparsity and irregularities. Existing methods strive to organize the points regularly, e.g. voxelize, pass them through a designed 2D/3D neural network, and then define object-level anchors that predict offsets of 3D bounding boxes using collective evidence from all the points on the objects of interest. Converse to the state-of-the-art anchor-based methods, based on the very same nature of data sparsity and irregularities, we observe that even points on an isolated object part are informative about position and orientation of the object. We thus argue in this paper for an approach opposite to existing methods using object-level anchors. Technically, we propose to represent an object as a collection of point cliques; one can intuitively think of these point cliques as hotspots, giving rise to the representation of Object as Hotspots (OHS). Based on OHS, we propose a Hotspot Network (HotSpotNet) that performs 3D object detection via firing of hotspots without setting the predefined bounding boxes. A distinctive feature of HotSpotNet is that it makes predictions directly from individual hotspots, and final results are obtained by aggregating these hotspot predictions. Experiments on the KITTI benchmark show the efficacy of our proposed OHS representation. Our one-stage, anchor-free HotSpotNet beats all other one-stage detectors by at least 2% on cars , cyclists and pedestrian for all difficulty levels. Notably, our proposed method performs better on small and difficult objects and we rank the first among all the submitted methods on pedestrian of KITTI test set.

Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection

In this work, we propose a novel method termed Frustum ConvNet (F-ConvNet) for amodal 3D object detection from point clouds. Given 2D region proposals in a RGB image, our method first generates a sequence of frustums for each region proposal, and uses the obtained frustums to group local points. F-ConvNet aggregates point-wise features as frustumlevel feature vectors, and arrays these feature vectors as a feature map for use of its subsequent component of fully convolutional network (FCN), which spatially fuses frustumlevel features and supports an end-to-end and continuous estimation of oriented boxes in the 3D space. We also propose component variants of L-ConvNet, including a FCN variant that extracts multi-resolution frustum features, and a refined use of L-ConvNet over a reduced 3D space. Careful ablation studies verify the efficacy of these component variants. LConvNet assumes no prior knowledge of the working 3D environment, and is thus dataset-agnostic. We present experiments on both the indoor SUN-RGBD and outdoor KITTI datasets. LConvNet outperforms all existing methods on SUN-RGBD, and at the time of submission it outperforms all published works on the KITTI benchmark. We will make the code of L-ConvNet publicly available.

Part-Aware Fine-grained Object Categorization using Weakly Supervised Part Detection Network

Fine-grained object categorization aims for distinguishing objects of subordinate categories that belong to the same entry-level object category. The task is challenging due to the facts that (1) training images with ground-truth labels are difficult to obtain, and (2) variations among different subordinate categories are subtle. It is well established that characterizing features of different subordinate categories are located on local parts of object instances. In fact, careful part annotations are available in many fine-grained categorization datasets. However, manually annotating object parts requires expertise, which is also difficult to generalize to new fine-grained categorization tasks. In this work, we propose a Weakly Supervised Part Detection Network (PartNet) that is able to detect discriminative local parts for use of fine-grained categorization. A vanilla PartNet builds on top of a base subnetwork two parallel streams of upper network layers, which respectively compute scores of classification probabilities (over subordinate categories) and detection probabilities (over a specified number of discriminative part detectors) for local regions of interest (RoIs). The image-level prediction is obtained by aggregating element-wise products of these region-level probabilities. To generate a diverse set of RoIs as inputs of PartNet, we propose a simple Discretized Part Proposals module (DPP) that directly targets for proposing candidates of discriminative local parts, with no bridging via object-level proposals. Experiments on the benchmark CUB-200-2011 and Oxford Flower 102 datasets show the efficacy of our proposed method for both discriminative part detection and fine-grained categorization. In particular, we achieve the new state-of-the-art performance on CUB-200-2011 dataset when ground-truth part annotations are not available.