By equipping the most recent 3D Gaussian Splatting representation with head 3D morphable models (3DMM), existing methods manage to create head avatars with high fidelity. However, most existing methods only reconstruct a head without the body, substantially limiting their application scenarios. We found that naively applying Gaussians to model the clothed chest and shoulders tends to result in blurry reconstruction and noisy floaters under novel poses. This is because of the fundamental limitation of Gaussians and point clouds -- each Gaussian or point can only have a single directional radiance without spatial variance, therefore an unnecessarily large number of them is required to represent complicated spatially varying texture, even for simple geometry. In contrast, we propose to model the body part with a neural texture that consists of coarse and pose-dependent fine colors. To properly render the body texture for each view and pose without accurate geometry nor UV mapping, we optimize another sparse set of Gaussians as anchors that constrain the neural warping field that maps image plane coordinates to the texture space. We demonstrate that Gaussian Head & Shoulders can fit the high-frequency details on the clothed upper body with high fidelity and potentially improve the accuracy and fidelity of the head region. We evaluate our method with casual phone-captured and internet videos and show our method archives superior reconstruction quality and robustness in both self and cross reenactment tasks. To fully utilize the efficient rendering speed of Gaussian splatting, we additionally propose an accelerated inference method of our trained model without Multi-Layer Perceptron (MLP) queries and reach a stable rendering speed of around 130 FPS for any subjects.
相關內容
As DeepFake video manipulation techniques escalate, posing profound threats, the urgent need to develop efficient detection strategies is underscored. However, one particular issue lies with facial images being mis-detected, often originating from degraded videos or adversarial attacks, leading to unexpected temporal artifacts that can undermine the efficacy of DeepFake video detection techniques. This paper introduces a novel method for robust DeepFake video detection, harnessing the power of the proposed Graph-Regularized Attentive Convolutional Entanglement (GRACE) based on the graph convolutional network with graph Laplacian to address the aforementioned challenges. First, conventional Convolution Neural Networks are deployed to perform spatiotemporal features for the entire video. Then, the spatial and temporal features are mutually entangled by constructing a graph with sparse constraint, enforcing essential features of valid face images in the noisy face sequences remaining, thus augmenting stability and performance for DeepFake video detection. Furthermore, the Graph Laplacian prior is proposed in the graph convolutional network to remove the noise pattern in the feature space to further improve the performance. Comprehensive experiments are conducted to illustrate that our proposed method delivers state-of-the-art performance in DeepFake video detection under noisy face sequences. The source code is available at //github.com/ming053l/GRACE.
We present our work on developing and training scalable graph foundation models (GFM) using HydraGNN, a multi-headed graph convolutional neural network architecture. HydraGNN expands the boundaries of graph neural network (GNN) in both training scale and data diversity. It abstracts over message passing algorithms, allowing both reproduction of and comparison across algorithmic innovations that define convolution in GNNs. This work discusses a series of optimizations that have allowed scaling up the GFM training to tens of thousands of GPUs on datasets that consist of hundreds of millions of graphs. Our GFMs use multi-task learning (MTL) to simultaneously learn graph-level and node-level properties of atomistic structures, such as the total energy and atomic forces. Using over 150 million atomistic structures for training, we illustrate the performance of our approach along with the lessons learned on two United States Department of Energy (US-DOE) supercomputers, namely the Perlmutter petascale system at the National Energy Research Scientific Computing Center and the Frontier exascale system at Oak Ridge National Laboratory. The HydraGNN architecture enables the GFM to achieve near-linear strong scaling performance using more than 2,000 GPUs on Perlmutter and 16,000 GPUs on Frontier. Hyperparameter optimization (HPO) was performed on over 64,000 GPUs on Frontier to select GFM architectures with high accuracy. Early stopping was applied on each GFM architecture for energy awareness in performing such an extreme-scale task. The training of an ensemble of highest-ranked GFM architectures continued until convergence to establish uncertainty quantification (UQ) capabilities with ensemble learning. Our contribution opens the door for rapidly developing, training, and deploying GFMs using large-scale computational resources to enable AI-accelerated materials discovery and design.
Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in how to effectively model and transfer the useful knowledge embedded in CLIP. Previous work mines the knowledge typically based on the limited visual samples and close-set semantics (i.e., within target category set of downstream task). However, the aligned CLIP image/text encoders contain abundant relationships between visual features and almost infinite open semantics, which may benefit the few-shot learning but remains unexplored. In this paper, we propose to mine open semantics as anchors to perform a relation transition from image-anchor relationship to image-target relationship to make predictions. Specifically, we adopt a transformer module which takes the visual feature as "Query", the text features of the anchors as "Key" and the similarity matrix between the text features of anchor and target classes as "Value". In this way, the output of such a transformer module represents the relationship between the image and target categories, i.e., the classification predictions. To avoid manually selecting the open semantics, we make the [CLASS] token of input text embedding learnable. We conduct extensive experiments on eleven representative classification datasets. The results show that our method performs favorably against previous state-of-the-arts considering few-shot classification settings.
Text-to-image (T2I) models achieve high-fidelity generation through extensive training on large datasets. However, these models may unintentionally pick up undesirable biases of their training data, such as over-representation of particular identities in gender or ethnicity neutral prompts. Existing alignment methods such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) fail to address this problem effectively because they operate on pairwise preferences consisting of individual samples, while the aforementioned biases can only be measured at a population level. For example, a single sample for the prompt "doctor" could be male or female, but a model generating predominantly male doctors even with repeated sampling reflects a gender bias. To address this limitation, we introduce PopAlign, a novel approach for population-level preference optimization, while standard optimization would prefer entire sets of samples over others. We further derive a stochastic lower bound that directly optimizes for individual samples from preferred populations over others for scalable training. Using human evaluation and standard image quality and bias metrics, we show that PopAlign significantly mitigates the bias of pretrained T2I models while largely preserving the generation quality. Code is available at //github.com/jacklishufan/PopAlignSDXL.
Current multimodal large language models (MLLMs) face significant challenges in visual document understanding (VDU) tasks due to the high resolution, dense text, and complex layouts typical of document images. These characteristics demand a high level of detail perception ability from MLLMs. While increasing input resolution improves detail perception, it also leads to longer sequences of visual tokens, increasing computational costs and straining the models' ability to handle long contexts. To address these challenges, we introduce DocKylin, a document-centric MLLM that performs visual content slimming at both the pixel and token levels, thereby reducing token sequence length in VDU scenarios. DocKylin utilizes an Adaptive Pixel Slimming (APS) preprocessing module to perform pixel-level slimming, increasing the proportion of informative pixels. Moreover, DocKylin incorporates a novel Dynamic Token Slimming (DTS) module to conduct token-level slimming, filtering essential tokens and removing others to create a compressed, adaptive visual sequence. Experiments demonstrate DocKylin's promising performance across various VDU benchmarks. Notably, both the proposed APS and DTS are parameter-free, facilitating easy integration into existing MLLMs, and our experiments indicate their potential for broader applications.
Utilizing Vision-Language Models (VLMs) for robotic manipulation represents a novel paradigm, aiming to enhance the model's ability to generalize to new objects and instructions. However, due to variations in camera specifications and mounting positions, existing methods exhibit significant performance disparities across different robotic platforms. To address this challenge, we propose RoboUniView in this paper, an innovative approach that decouples visual feature extraction from action learning. We first learn a unified view representation from multi-perspective views by pre-training on readily accessible data, and then derive actions from this unified view representation to control robotic manipulation. This unified view representation more accurately mirrors the physical world and is not constrained by the robotic platform's camera parameters. Thanks to this methodology, we achieve state-of-the-art performance on the demanding CALVIN benchmark, enhancing the success rate in the $D \to D$ setting from 88.7% to 96.2%, and in the $ABC \to D$ setting from 82.4% to 94.2%. Moreover, our model exhibits outstanding adaptability and flexibility: it maintains high performance under unseen camera parameters, can utilize multiple datasets with varying camera parameters, and is capable of joint cross-task learning across datasets. Code is provided for re-implementation. //github.com/liufanfanlff/RoboUniview
Recently, very large language models (LLMs) have shown exceptional performance on several English NLP tasks with just in-context learning (ICL), but their utility in other languages is still underexplored. We investigate their effectiveness for NLP tasks in low-resource languages (LRLs), especially in the setting of zero-labelled cross-lingual transfer (0-CLT), where no labelled training data for the target language is available -- however training data from one or more related medium-resource languages (MRLs) is utilized, alongside the available unlabeled test data for a target language. We introduce Self-Supervised Prompting (SSP), a novel ICL approach tailored for the 0-CLT setting. SSP is based on the key observation that LLMs output more accurate labels if in-context exemplars are from the target language (even if their labels are slightly noisy). To operationalize this, since target language training data is not available in 0-CLT, SSP operates in two stages. In Stage I, using source MRL training data, target language's test data is noisily labeled. In Stage II, these noisy test data points are used as exemplars in ICL for further improved labelling. Additionally, our implementation of SSP uses a novel Integer Linear Programming (ILP)-based exemplar selection that balances similarity, prediction confidence (when available) and label coverage. Experiments on three tasks and eleven LRLs (from three regions) demonstrate that SSP strongly outperforms existing SOTA fine-tuned and prompting-based baselines in 0-CLT setup.
The recent advancements in text-to-image generative models have been remarkable. Yet, the field suffers from a lack of evaluation metrics that accurately reflect the performance of these models, particularly lacking fine-grained metrics that can guide the optimization of the models. In this paper, we propose EvalAlign, a metric characterized by its accuracy, stability, and fine granularity. Our approach leverages the capabilities of Multimodal Large Language Models (MLLMs) pre-trained on extensive datasets. We develop evaluation protocols that focus on two key dimensions: image faithfulness and text-image alignment. Each protocol comprises a set of detailed, fine-grained instructions linked to specific scoring options, enabling precise manual scoring of the generated images. We Supervised Fine-Tune (SFT) the MLLM to align closely with human evaluative judgments, resulting in a robust evaluation model. Our comprehensive tests across 24 text-to-image generation models demonstrate that EvalAlign not only provides superior metric stability but also aligns more closely with human preferences than existing metrics, confirming its effectiveness and utility in model assessment.
Unified speech-text models like SpeechGPT, VioLA, and AudioPaLM have shown impressive performance across various speech-related tasks, especially in Automatic Speech Recognition (ASR). These models typically adopt a unified method to model discrete speech and text tokens, followed by training a decoder-only transformer. However, they are all designed for non-streaming ASR tasks, where the entire speech utterance is needed during decoding. Hence, we introduce a decoder-only model exclusively designed for streaming recognition, incorporating a dedicated boundary token to facilitate streaming recognition and employing causal attention masking during the training phase. Furthermore, we introduce right-chunk attention and various data augmentation techniques to improve the model's contextual modeling abilities. While achieving streaming speech recognition, experiments on the AISHELL-1 and -2 datasets demonstrate the competitive performance of our streaming approach with non-streaming decoder-only counterparts.
Diffusion models (DMs) have shown great potential for high-quality image synthesis. However, when it comes to producing images with complex scenes, how to properly describe both image global structures and object details remains a challenging task. In this paper, we present Frido, a Feature Pyramid Diffusion model performing a multi-scale coarse-to-fine denoising process for image synthesis. Our model decomposes an input image into scale-dependent vector quantized features, followed by a coarse-to-fine gating for producing image output. During the above multi-scale representation learning stage, additional input conditions like text, scene graph, or image layout can be further exploited. Thus, Frido can be also applied for conditional or cross-modality image synthesis. We conduct extensive experiments over various unconditioned and conditional image generation tasks, ranging from text-to-image synthesis, layout-to-image, scene-graph-to-image, to label-to-image. More specifically, we achieved state-of-the-art FID scores on five benchmarks, namely layout-to-image on COCO and OpenImages, scene-graph-to-image on COCO and Visual Genome, and label-to-image on COCO. Code is available at //github.com/davidhalladay/Frido.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191