United States

While progress has been made in the field of portrait reenactment, the problem of how to produce high-fidelity and robust videos remains. Recent studies normally find it challenging to handle rarely seen target poses due to the limitation of source data. This paper proposes the Video Portrait via Non-local Quantization Modeling (VPNQ) framework, which produces pose- and disturbance-robust reenactable video portraits. Our key insight is to learn position-invariant quantized local patch representations and build a mapping between simple driving signals and local textures with non-local spatial-temporal modeling. Specifically, instead of learning a universal quantized codebook, we identify that a personalized one can be trained to preserve desired position-invariant local details better. Then, a simple representation of projected landmarks can be used as sufficient driving signals to avoid 3D rendering. Following, we employ a carefully designed Spatio-Temporal Transformer to predict reasonable and temporally consistent quantized tokens from the driving signal. The predicted codes can be decoded back to robust and high-quality videos. Comprehensive experiments have been conducted to validate the effectiveness of our approach.

AAAI 2023

Robust Video Portrait Reenactment via Personalized Representation Quantization

video transformer

face reenactment

vector quantization

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

poster

Measuring the perception of visual content is a long-standing problem in computer vision. Many mathematical models have been developed to evaluate the look or quality of an image. Despite the effectiveness of such tools in quantifying degradations such as noise and blurriness levels, such quantification is loosely coupled with human language. When it comes to more abstract perception about the feel of visual content, existing methods can only rely on supervised models that are explicitly trained with labeled data collected via laborious user study. In this paper, we go beyond the conventional paradigms by exploring the rich visual language prior encapsulated in Contrastive Language-Image Pre-training (CLIP) models for assessing both the quality perception (look) and abstract perception (feel) of images without explicit task-specific training. In particular, we discuss effective prompt designs and show an effective prompt pairing strategy to harness the prior. We also provide extensive experiments on controlled datasets and Image Quality Assessment (IQA) benchmarks. Our results show that CLIP captures meaningful priors that generalize well to different perceptual assessments.

Exploring CLIP for Assessing the Look and Feel of Images

Video salient object detection (VSOD), as a fundamental computer vision problem, has been extensively discussed in the last decade. However, all existing works focus on addressing the VSOD problem in 2D scenarios. With the rapid development of VR devices, panoramic videos have been a promising alternative to 2D videos to provide immersive feelings of the real world. In this paper, we aim to tackle the video salient object detection problem for panoramic videos, with their corresponding ambisonic audios. A multimodal fusion module equipped with two pseudo-siamese audio-visual context fusion (ACF) blocks is proposed to effectively conduct audio-visual interaction. The ACF block equipped with spherical positional encoding enables the fusion in the 3D context to capture the spatial correspondence between pixels and sound sources from the equirectangular frames and ambisonic audios. Experimental results verify the effectiveness of our proposed components and demonstrate that our method achieves state-of-the-art performance on the ASOD60K dataset.

Panoramic Video Salient Object Detection with Ambisonic Audio Guidance

In computer vision, it has achieved great transfer learning performance via adapting large-scale pretrained vision models (e.g., vision transformers) to downstream tasks. Common approaches for model adaptation either update all model parameters or leverage linear probes. In this paper, we aim to study parameter-efficient model adaptation strategies for vision transformers on the image classification task. We formulate efficient model adaptation as a subspace training problem and perform a comprehensive benchmarking over different efficient adaptation methods. We conduct an empirical study on each efficient model adaptation method focusing on its performance alongside parameter cost. Furthermore, we propose a parameter-efficient model adaptation framework, which first selects submodules by measuring local intrinsic dimensions and then projects them into subspace for further decomposition via a novel Kronecker Adaptation method. We analyze and compare our method with a diverse set of baseline model adaptation methods (including state-of-the-art methods for pretrained language models). Our method performs the best in terms of the tradeoff between accuracy and parameter efficiency across 20 datasets under the few-shot setting and 7 image classification datasets under the full-shot setting. 

Parameter-efficient Model Adaptation for Vision Transformers

Arbitrary neural style transfer has been a popular research topic due to its rich application scenarios. Effective disentanglement of content and style is the critical factor for synthesizing an image with arbitrary style. The existing methods focus on disentangling feature representations of content and style in the spatial domain where the content and style components are innately entangled and difficult to be disentangled clearly. Therefore, these methods always suffer from low-quality results because of the sub-optimal disentanglement. To address such a challenge, this paper proposes the frequency mixer (FreMixer) module that disentangles and re-entangles the frequency spectrum of content and style components in the frequency domain. Since content and style components have different frequency-domain characteristics (\emph{e.g.} frequency bands and frequency patterns), the FreMixer could well disentangle these two components. Based on the FreMixer module, we design a novel Frequency Domain Disentanglement (FDD) framework for arbitrary neural style transfer. Qualitative and quantitative experiments verify that the proposed method can render better stylized results compared to the state-of-the-art methods.

Frequency Domain Disentanglement for Arbitrary Neural Style Transfer

Video object detection (VID) is challenging because of the high variation of object appearance as well as the diverse deterioration in some frames. On the positive side, the detection in a certain frame of a video, compared with that in a still image, can draw support from other frames. Hence, how to aggregate features across different frames is pivotal to the VID problem. Most of existing aggregation algorithms are customized for two-stage detectors. But, the detectors in this category are usually computationally expensive due to the two-stage nature. This work proposes a simple yet effective strategy to address the above concerns, which spends marginal overheads with significant gains in accuracy. Concretely, different from the traditional two-stage pipeline, we advocate putting the region-level selection after the one-stage detection to avoid processing massive low-quality candidates. Besides, a novel module is constructed to evaluate the relationship between a target frame and its reference ones, and guide the aggregation. Extensive experiments and ablation studies are conducted to verify the efficacy of our design, and reveal its superiority over other state-of-the-art VID approaches in both effectiveness and efficiency. Our YOLOX-based model can achieve promising performance (\emph{e.g.}, 87.5\% AP50 at over 30 FPS on the ImageNet VID dataset on a single 2080Ti GPU), making it attractive for large-scale or real-time applications. The implementation is simple, we have made the demo codes and models available at \url{https://github.com/YuHengsss/YOLOV}.

YOLOV: Making Still Image Object Detectors Great at Video Object Detection

Generative models for learning combinatorial structures have transformative impacts in many applications. However, existing approaches fail to offer efficient and accurate learning results. Because the learning objective is subject to combinatorial constraints, the gradient estimation of the objective is highly intractable. Existing gradient estimation methods would easily run into exponential time/memory space, or incur huge estimation errors due to improper approximation. For this, we develop NEural Lovasz Sampler (NELSON), a neural network based on Lovasz Local Lemma (LLL). We show it guarantees to generate samples satisfying combinatorial constraints from the distribution of the constrained Markov Random Fields model (MRF) under certain conditions. We further present a fully differentiable contrastive divergence-based learning framework on constrained MRF (NELSON-CD). Meanwhile, NELSON-CD being fully differentiable allows us to take advantage of the parallel computing power of GPUs, resulting in great efficiency. Experimental results on three real-world combinatorial problems reveal that NELSON learns to generate 100% valid structures. In comparison, baselines either time out on large-size data sets or fail to generate valid structures, whereas NELSON scales much better with problem size. In addition, NELSON outperforms baselines in various learning metrics, such as log-likelihood and MAP scores.

Learning Combinatorial Structures via Markov Random Fields with Sampling through Lovasz Local Lemma

Pretrained vision models for object recognition often suffer a dramatic performance drop with degradations unseen during training. In this work, we propose a RObust FEature Rectification module (ROFER) to improve the performance of pretrained models against degradations. Specifically, ROFER first estimates the type and intensity of the degradation that corrupts the image features. Then, it leverages a Fully Convolutional Network (FCN) to rectify the features from the degradation by pulling them back to clear features. ROFER is a general-purpose module that can address various degradations simultaneously, including blur, noise, and low contrast. Besides, it can be plugged into pretrained models seamlessly to rectify the degraded features without retraining the whole model. Furthermore, ROFER can be easily extended to address composite degradations by adopting a beam search algorithm to find the composition order. Evaluations on CIFAR-10 and Tiny-ImageNet demonstrate that the accuracy of ROFER is 5% higher than that of SOTA methods on different degradations. With respect to composite degradations, ROFER improves the accuracy of a pretrained CNN by 10% and 6% on CIFAR-10 and Tiny-ImageNet respectively.

Robust Feature Rectification of Pretrained Vision Models for Object Recognition

Stochastic human motion prediction aims to forecast multiple plausible future motions given a single pose sequence from the past. Most previous works focus on designing elaborate losses to improve the accuracy, while the diversity is typically characterized by randomly sampling a set of latent variables from the latent prior, which is then decoded into possible motions. This joint training of sampling and decoding, however, suffers from posterior collapse as the learned latent variables tend to be ignored by a strong decoder, leading to limited diversity. Alternatively, inspired by the diffusion process in nonequilibrium thermodynamics, we propose MotionDiff, a diffusion probabilistic model to treat the kinematics of human joints as heated particles, which will diffuse from original states to a noise distribution. This process not only offers a natural way to obtain the "whitened'' latents without any trainable parameters, but also introduces a new noise in each diffusion step, both of which facilitate more diverse motions. Human motion prediction is then regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence. Specifically, MotionDiff consists of two parts: a spatial-temporal transformer-based diffusion network to generate diverse yet plausible motions, and a flexible refinement network to further enable geometric losses and align with the ground truth. Experimental results on two datasets demonstrate that our model yields the competitive performance in terms of both diversity and accuracy. 

Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction

Network binarization (i.e., binary neural networks, BNNs) can efficiently compress deep neural networks and accelerate model inference but cause severe accuracy degradation. Existing BNNs are mainly implemented based on the commonly used full-precision network backbones, and then the accuracy is improved with various techniques. However, there is a question of whether the full-precision network backbone is well adapted to BNNs. We start from the factors of the performance degradation of BNNs and analyze the problems of directly using full-precision network backbones for BNNs: for a given computational budget, the backbone of a BNN may need to be shallower and wider compared to the backbone of a full-precision network. With this in mind, Depth-Width Reshaping (DWR) is proposed to reshape the depth and width of existing full-precision network backbones and further optimize them by incorporating pruning techniques to better fit the BNNs. Extensive experiments demonstrate the analytical result and the effectiveness of the proposed method. Compared with the original backbones, the DWR backbones constructed by the proposed method result in close to $O(\sqrt s )$ decrease in activations, while achieving an absolute accuracy increase by up to 1.7\% with comparable computational cost. Besides, by using the DWR backbones, existing methods can achieve new state-of-the-art (SOTA) accuracy (e.g., 67.2\% on ImageNet with ResNet-18 as the original backbone). We hope this work provides a novel insight into the backbone design of BNNs. The code is available at https://github.com/pingxue-hfut/DWR.

Fast and Accurate Binary Neural Networks based on Depth-Width Reshaping

Depth map super-resolution (DSR) has been a fundamental task for 3D computer vision. While arbitrary scale DSR is a more realistic setting in this scenario, previous approaches predominantly suffer from the issue of inefficient real-numbered scale upsampling. To explicitly address this issue, we propose a novel continuous depth representation for DSR. The heart of this representation is our proposed Geometric Spatial Aggregator (GSA), which exploits a distance field modulated by arbitrarily upsampled target gridding, through which the geometric information is explicitly introduced into feature aggregation and target generation. Furthermore, bricking with GSA, we present a transformer-style backbone named GeoDSR, which possesses a principled way to construct the functional mapping between local coordinates and the high-resolution output results, empowering our model with the advantage of arbitrary shape transformation ready to help diverse zooming demand. Extensive experimental results on standard depth map benchmarks, e.g., NYU v2, have demonstrated that the proposed framework achieves significant restoration gain in arbitrary scale depth map super-resolution compared with the prior art. Our codes are available at https://github.com/nana01219/GeoDSR.

Robust Video Portrait Reenactment via Personalized Representation Quantization

Downloads

Next from AAAI 2023

Exploring CLIP for Assessing the Look and Feel of Images

Similar lecture

JR2Net: Joint Monocular 3D Face Reconstruction and Reenactment