Zhao Wang

Shizhan Gong, Yuan Zhong, Wenao Ma et al.

Despite that the segment anything model (SAM) achieved impressive results on general-purpose semantic segmentation with strong generalization ability on daily images, its demonstrated performance on medical image segmentation is less precise and not stable, especially when dealing with tumor segmentation tasks that involve objects of small sizes, irregular shapes, and low contrast. Notably, the original SAM architecture is designed for 2D natural images, therefore would not be able to extract the 3D spatial information from volumetric medical data effectively. In this paper, we propose a novel adaptation method for transferring SAM from 2D to 3D for promptable medical image segmentation. Through a holistically designed scheme for architecture modification, we transfer the SAM to support volumetric inputs while retaining the majority of its pre-trained parameters for reuse. The fine-tuning process is conducted in a parameter-efficient manner, wherein most of the pre-trained parameters remain frozen, and only a few lightweight spatial adapters are introduced and tuned. Regardless of the domain gap between natural and medical data and the disparity in the spatial arrangement between 2D and 3D, the transformer trained on natural images can effectively capture the spatial patterns present in volumetric medical images with only lightweight adaptations. We conduct experiments on four open-source tumor segmentation datasets, and with a single click prompt, our model can outperform domain state-of-the-art medical image segmentation models on 3 out of 4 tasks, specifically by 8.25%, 29.87%, and 10.11% for kidney tumor, pancreas tumor, colon cancer segmentation, and achieve similar performance for liver tumor segmentation. We also compare our adaptation method with existing popular adapters, and observed significant performance improvement on most datasets.

Wang Zhao, Shaohui Liu, Hengkai Guo et al.

Estimating the pose of a moving camera from monocular video is a challenging problem, especially due to the presence of moving objects in dynamic environments, where the performance of existing camera pose estimation methods are susceptible to pixels that are not geometrically consistent. To tackle this challenge, we present a robust dense indirect structure-from-motion method for videos that is based on dense correspondence initialized from pairwise optical flow. Our key idea is to optimize long-range video correspondence as dense point trajectories and use it to learn robust estimation of motion segmentation. A novel neural network architecture is proposed for processing irregular point trajectory data. Camera poses are then estimated and optimized with global bundle adjustment over the portion of long-range point trajectories that are classified as static. Experiments on MPI Sintel dataset show that our system produces significantly more accurate camera trajectories compared to existing state-of-the-art methods. In addition, our method is able to retain reasonable accuracy of camera poses on fully static scenes, which consistently outperforms strong state-of-the-art dense correspondence based methods with end-to-end deep learning, demonstrating the potential of dense indirect methods based on optical flow and point trajectories. As the point trajectory representation is general, we further present results and comparisons on in-the-wild monocular videos with complex motion of dynamic objects. Code is available at https://github.com/bytedance/particle-sfm.

Shaoning Xiao, Long Chen, Kaifeng Gao et al.

Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA).The major stumbling block to achieve this purpose is the semantic gap between language and video since they are at different levels of abstraction. Existing efforts mainly focus on designing sophisticated architectures while utilizing frame- or object-level visual representations. In this paper, we reconsider the multi-modal alignment problem in VideoQA from feature and sample perspectives to achieve better performance. From the view of feature,we break down the video into trajectories and first leverage trajectory feature in VideoQA to enhance the alignment between two modalities. Moreover, we adopt a heterogeneous graph architecture and design a hierarchical framework to align both trajectory-level and frame-level visual feature with language feature. In addition, we found that VideoQA models are largely dependent on language priors and always neglect visual-language interactions. Thus, two effective yet portable training augmentation strategies are designed to strengthen the cross-modal correspondence ability of our model from the view of sample. Extensive results show that our method outperforms all the state-of-the-art models on the challenging NExT-QA benchmark, which demonstrates the effectiveness of the proposed method.

Bolin Chen, Zhao Wang, Binzhe Li et al.

In this paper, we propose a novel framework for Interactive Face Video Coding (IFVC), which allows humans to interact with the intrinsic visual representations instead of the signals. The proposed solution enjoys several distinct advantages, including ultra-compact representation, low delay interaction, and vivid expression/headpose animation. In particular, we propose the Internal Dimension Increase (IDI) based representation, greatly enhancing the fidelity and flexibility in rendering the appearance while maintaining reasonable representation cost. By leveraging strong statistical regularities, the visual signals can be effectively projected into controllable semantics in the three dimensional space (e.g., mouth motion, eye blinking, head rotation, head translation and head location), which are compressed and transmitted. The editable bitstream, which naturally supports the interactivity at the semantic level, can synthesize the face frames via the strong inference ability of the deep generative model. Experimental results have demonstrated the performance superiority and application prospects of our proposed IFVC scheme. In particular, the proposed scheme not only outperforms the state-of-the-art video coding standard Versatile Video Coding (VVC) and the latest generative compression schemes in terms of rate-distortion performance for face videos, but also enables the interactive coding without introducing additional manipulation processes. Furthermore, the proposed framework is expected to shed lights on the future design of the digital human communication in the metaverse.

Yuka Hashimoto, Zhao Wang, Tomoko Matsui

We propose a new framework that generalizes the parameters of neural network models to $C^*$-algebra-valued ones. $C^*$-algebra is a generalization of the space of complex numbers. A typical example is the space of continuous functions on a compact space. This generalization enables us to combine multiple models continuously and use tools for functions such as regression and integration. Consequently, we can learn features of data efficiently and adapt the models to problems continuously. We apply our framework to practical problems such as density estimation and few-shot learning and show that our framework enables us to learn features of data even with a limited number of samples. Our new framework highlights the potential possibility of applying the theory of $C^*$-algebra to general neural network models.

Wang Zhao, Yan-Pei Cao, Jiale Xu et al.

Procedural Content Generation (PCG) is powerful in creating high-quality 3D contents, yet controlling it to produce desired shapes is difficult and often requires extensive parameter tuning. Inverse Procedural Content Generation aims to automatically find the best parameters under the input condition. However, existing sampling-based and neural network-based methods still suffer from numerous sample iterations or limited controllability. In this work, we present DI-PCG, a novel and efficient method for Inverse PCG from general image conditions. At its core is a lightweight diffusion transformer model, where PCG parameters are directly treated as the denoising target and the observed images as conditions to control parameter generation. DI-PCG is efficient and effective. With only 7.6M network parameters and 30 GPU hours to train, it demonstrates superior performance in recovering parameters accurately, and generalizing well to in-the-wild images. Quantitative and qualitative experiment results validate the effectiveness of DI-PCG in inverse PCG and image-to-3D generation tasks. DI-PCG offers a promising approach for efficient inverse PCG and represents a valuable exploration step towards a 3D generation path that models how to construct a 3D asset using parametric models.

Ziqun Li, Qi Zhang, Xiaofeng Huang et al.

High-efficient image compression is a critical requirement. In several scenarios where multiple modalities of data are captured by different sensors, the auxiliary information from other modalities are not fully leveraged by existing image-only codecs, leading to suboptimal compression efficiency. In this paper, we increase image compression performance with the assistance of point cloud, which is widely adopted in the area of autonomous driving. We first unify the data representation for both modalities to facilitate data processing. Then, we propose the point cloud-assisted neural image codec (PCA-NIC) to enhance the preservation of image texture and structure by utilizing the high-dimensional point cloud information. We further introduce a multi-modal feature fusion transform module (MMFFT) to capture more representative image features, remove redundant information between channels and modalities that are not relevant to the image content. Our work is the first to improve image compression performance using point cloud and achieves state-of-the-art performance.

Shurun Wang, Zhao Wang, Shiqi Wang et al.

The visual signal compression is a long-standing problem. Fueled by the recent advances of deep learning, exciting progress has been made. Despite better compression performance, existing end-to-end compression algorithms are still designed towards better signal quality in terms of rate-distortion optimization. In this paper, we show that the design and optimization of network architecture could be further improved for compression towards machine vision. We propose an inverted bottleneck structure for the encoder of the end-to-end compression towards machine vision, which specifically accounts for efficient representation of the semantic information. Moreover, we quest the capability of optimization by incorporating the analytics accuracy into the optimization process, and the optimality is further explored with generalized rate-accuracy optimization in an iterative manner. We use object detection as a showcase for end-to-end compression towards machine vision, and extensive experiments show that the proposed scheme achieves significant BD-rate savings in terms of analysis performance. Moreover, the promise of the scheme is also demonstrated with strong generalization capability towards other machine vision tasks, due to the enabling of signal-level reconstruction.

Zhao Wang, Changyue Ma, Yan Ye

Video compression is a basic requirement for consumer and professional video applications alike. Video coding standards such as H.264/AVC and H.265/HEVC are widely deployed in the market to enable efficient use of bandwidth and storage for many video applications. To reduce the coding artifacts and improve the compression efficiency, neural network based loop filtering of the reconstructed video has been developed in the literature. However, loop filtering is a challenging task due to the variation in video content and sampling densities. In this paper, we propose a on-line scaling based multi-density attention network for loop filtering in video compression. The core of our approach lies in several aspects: (a) parallel multi-resolution convolution streams for extracting multi-density features, (b) single attention branch to learn the sample correlations and generate mask maps, (c) a channel-mutual attention procedure to fuse the data from multiple branches, (d) on-line scaling technique to further optimize the output results of network according to the actual signal. The proposed multi-density attention network learns rich features from multiple sampling densities and performs robustly on video content of different resolutions. Moreover, the online scaling process enhances the signal adaptability of the off-line pre-trained model. Experimental results show that 10.18% bit-rate reduction at the same video quality can be achieved over the latest Versatile Video Coding (VVC) standard. The objective performance of the proposed algorithm outperforms the state-of-the-art methods and the subjective quality improvement is obvious in terms of detail preservation and artifact alleviation.

Jixiang Li, Chuming Liang, Bo Zhang et al.

Convolutional neural networks are widely adopted in Acoustic Scene Classification (ASC) tasks, but they generally carry a heavy computational burden. In this work, we propose a lightweight yet high-performing baseline network inspired by MobileNetV2, which replaces square convolutional kernels with unidirectional ones to extract features alternately in temporal and frequency dimensions. Furthermore, we explore a dynamic architecture space built on the basis of the proposed baseline with the recent Neural Architecture Search (NAS) paradigm, which first trains a supernet that incorporates all candidate networks and then applies a well-known evolutionary algorithm NSGA-II to discover more efficient networks with higher accuracy and lower computational cost. Experimental results demonstrate that our searched network is competent in ASC tasks, which achieves 90.3% F1-score on the DCASE2018 task 5 evaluation set, marking a new state-of-the-art performance while saving 25% of FLOPs compared to our baseline network.