IceDiff: High Resolution and High-Quality Sea Ice Forecasting with Generative Diffusion Prior

Variation of Arctic sea ice has significant impacts on polar ecosystems, transporting routes, coastal communities, and global climate. Tracing the change of sea ice at a finer scale is paramount for both operational applications and scientific studies. Recent pan-Arctic sea ice forecasting methods that leverage advances in artificial intelligence has made promising progress over numerical models. However, forecasting sea ice at higher resolutions is still under-explored. To bridge the gap, we propose a two-staged deep learning framework, IceDiff, to forecast sea ice concentration at finer scales. IceDiff first leverages an independently trained vision transformer to generate coarse yet superior forecasting over previous methods at a regular 25km x 25km grid. This high-quality sea ice forecasting can be utilized as reliable guidance for the next stage. Subsequently, an unconditional diffusion model pre-trained on sea ice concentration maps is utilized for sampling down-scaled sea ice forecasting via a zero-shot guided sampling strategy and a patch-based method. For the first time, IceDiff demonstrates sea ice forecasting with the 6.25km x 6.25km resolution. IceDiff extends the boundary of existing sea ice forecasting models and more importantly, its capability to generate high-resolution sea ice concentration data is vital for pragmatic usages and research.

Learning Frame-Wise Emotion Intensity for Audio-Driven Talking-Head Generation

Human emotional expression is inherently dynamic, complex, and fluid, characterized by smooth transitions in intensity throughout verbal communication. However, the modeling of such intensity fluctuations has been largely overlooked by previous audio-driven talking-head generation methods, which often results in static emotional outputs. In this paper, we explore how emotion intensity fluctuates during speech, proposing a method for capturing and generating these subtle shifts for talking-head generation. Specifically, we develop a talking-head framework that is capable of generating a variety of emotions with precise control over intensity levels. This is achieved by learning a continuous emotion latent space, where emotion types are encoded within latent orientations and emotion intensity is reflected in latent norms. In addition, to capture the dynamic intensity fluctuations, we adopt an audio-to-intensity predictor by considering the speaking tone that reflects the intensity. The training signals for this predictor are obtained through our emotion-agnostic intensity pseudo-labeling method without the need of frame-wise intensity labeling. Extensive experiments and analyses validate the effectiveness of our proposed method in accurately capturing and reproducing emotion intensity fluctuations in talking-head generation, thereby significantly enhancing the expressiveness and realism of the generated outputs.

GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning

Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate augmentation for effective feature learning. To address these challenges, we propose GS-PT, which integrates 3D Gaussian Splatting (3DGS) into point cloud self-supervised learning for the first time. Our pipeline utilizes transformers as the backbone for self-supervised pre-training and introduces novel contrastive learning tasks through 3DGS. Specifically, the transformers aim to reconstruct the masked point cloud. 3DGS utilizes multi-view rendered images as input to generate enhanced point cloud distributions and novel view images, facilitating data augmentation and cross-modal contrastive learning. Additionally, we incorporate features from depth maps. By optimizing these tasks collectively, our method enriches the tri-modal self-supervised learning process, enabling the model to leverage the correlation across 3D point clouds and 2D images from various modalities. We freeze the encoder after pre-training and test the model's performance on multiple downstream tasks. Experimental results indicate that GS-PT outperforms the off-the-shelf self-supervised learning methods on various downstream tasks including 3D object classification, real-world classifications, and few-shot learning and segmentation.

MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videos

Understanding human intentions and actions through egocentric videos is important on the path to embodied artificial intelligence. As a branch of egocentric vision techniques, hand trajectory prediction plays a vital role in comprehending human motion patterns, benefiting downstream tasks in extended reality and robot manipulation. However, capturing high-level human intentions consistent with reasonable temporal causality is challenging when only egocentric videos are available. This difficulty is exacerbated under camera egomotion interference and the absence of affordance labels to explicitly guide the optimization of hand waypoint distribution. In this work, we propose a novel hand trajectory prediction method dubbed MADiff, which forecasts future hand waypoints with diffusion models. The devised denoising operation in the latent space is achieved by our proposed motion-aware Mamba, where the camera wearer's egomotion is integrated to achieve motion-driven selective scan (MDSS). To discern the relationship between hands and scenarios without explicit affordance supervision, we leverage a foundation model that fuses visual and language features to capture high-level semantics from video clips. Comprehensive experiments conducted on five public datasets with the existing and our proposed new evaluation metrics demonstrate that MADiff predicts comparably reasonable hand trajectories compared to the state-of-the-art baselines, and achieves real-time performance. We will release our code and pretrained models of MADiff at the project page: https://irmvlab.github.io/madiff.github.io.

Assessing Sample Quality via the Latent Space of Generative Models

Advances in generative models increase the need for sample quality assessment. To do so, previous methods rely on a pre-trained feature extractor to embed the generated samples and real samples into a common space for comparison. However, different feature extractors might lead to inconsistent assessment outcomes. Moreover, these methods are not applicable for domains where a robust, universal feature extractor does not yet exist, such as medical images or 3D assets. In this paper, we propose to directly examine the latent space of the trained generative model to infer generated sample quality. This is feasible because the quality a generated sample directly relates to the amount of training data resembling it, and we can infer this information by examining the density of the latent space. Accordingly, we use a latent density score function to quantify sample quality. We show that the proposed score correlates highly with the sample quality for various generative models including VAEs, GANs and Latent Diffusion Models. Compared with previous quality assessment methods, our method has the following advantages: 1) pre-generation quality estimation with reduced computational cost, 2) generalizability to various domains and modalities, and 3) applicability to latent-based image editing and generation methods. Extensive experiments demonstrate that our proposed methods can benefit downstream tasks such as few-shot image classification and latent face image editing. Code is available at https://github.com/cvlab-stonybrook/LS-sample-quality.

RefGaussian: Disentangling Reflections from 3D Gaussian Splatting for Realistic Rendering

3D Gaussian Splatting (3D-GS) has made a notable advancement in the field of neural rendering, 3D scene reconstruction, and novel view synthesis. Nevertheless, 3D-GS encounters the main challenge when it comes to accurately representing physical reflections, especially in the case of total reflection and semi-reflection that are commonly found in real-world scenes. This limitation causes reflections to be mistakenly treated as independent elements with physical presence, leading to imprecise reconstructions. Herein, to tackle this challenge, we propose RefGaussian to disentangle reflections from 3D-GS for realistically modeling reflections. Specifically, we propose to split a scene into transmitted and reflected components and represent these components using two Spherical Harmonics (SH). Given that this decomposition is not fully determined, we employ local regularization techniques to ensure local smoothness for both the transmitted and reflected components, thereby achieving more plausible decomposition outcomes than 3D-GS. Experimental results demonstrate that our approach achieves superior novel view synthesis and accurate depth estimation outcomes. Furthermore, it enables the utilization of scene editing applications, ensuring both high-quality results and physical coherence.

MFA-Net: Multi-Scale feature fusion attention network for liver tumor segmentation

Segmentation of organs of interest in medical CT images is beneficial for diagnosis of diseases. Though recent methods based on Fully Convolutional Neural Networks (F-CNNs) have shown success in many segmentation tasks, fusing features from images with different scales is still a challenge: (1) Due to the lack of spatial awareness, F-CNNs share the same weights at different spatial locations. (2) F-CNNs can only obtain surrounding information through local receptive fields. To address the above challenge, we propose a new segmentation framework based on attention mechanisms, named MFA-Net (Multi-Scale Feature Fusion Attention Network). The proposed framework can learn more meaningful feature maps among multiple scales and result in more accurate automatic segmentation. We compare our proposed MFA-Net with SOTA methods on two 2D liver CT datasets. The experimental results show that our MFA-Net produces more precise segmentation on images with different scales.

Diff-IP2D: Diffusion-Based Hand-Object Interaction Prediction on Egocentric Videos

Understanding how humans would behave during hand-object interaction is vital for applications in service robot manipulation and extended reality. To achieve this, some recent works have been proposed to simultaneously predict hand trajectories and object affordances on human egocentric videos. They are regarded as the representation of future hand-object interactions, indicating potential human motion and motivation. However, the existing approaches mostly adopt the autoregressive paradigm for unidirectional prediction, which lacks mutual constraints within the holistic future sequence, and accumulates errors along the time axis. Meanwhile, these works basically overlook the effect of camera egomotion on first-person view predictions. To address these limitations, we propose a novel diffusion-based interaction prediction method, namely Diff-IP2D, to forecast future hand trajectories and object affordances concurrently in an iterative non-autoregressive manner. We transform the sequential 2D images into latent feature space and design a denoising diffusion model to predict future latent interaction features conditioned on past ones. Motion features are further integrated into the conditional denoising process to enable Diff-IP2D aware of the camera wearer's dynamics for more accurate interaction prediction. The experimental results show that our method significantly outperforms the state-of-the-art baselines on both the off-the-shelf metrics and our proposed new evaluation protocol. This highlights the efficacy of leveraging a generative paradigm for 2D hand-object interaction prediction. The code of Diff-IP2D will be released at https://github.com/IRMVLab/Diff-IP2D.

Unifying Lane-Level Traffic Prediction from a Graph Structural Perspective: Benchmark and Baseline

Traffic prediction has long been a focal and pivotal area in research, witnessing both significant strides from city-level to road-level predictions in recent years. With the advancement of Vehicle-to-Everything (V2X) technologies, autonomous driving, and large-scale models in the traffic domain, lane-level traffic prediction has emerged as an indispensable direction. However, further progress in this field is hindered by the absence of comprehensive and unified evaluation standards, coupled with limited public availability of data and code. This paper extensively analyzes and categorizes existing research in lane-level traffic prediction, establishes a unified spatial topology structure and prediction tasks, and introduces a simple baseline model, GraphMLP, based on graph structure and MLP networks. We have replicated codes not publicly available in existing studies and, based on this, thoroughly and fairly assessed various models in terms of effectiveness, efficiency, and applicability, providing insights for practical applications. Additionally, we have released three new datasets and corresponding codes to accelerate progress in this field, all of which can be found on https://github.com/ShuhaoLii/TITS24LaneLevel-Traffic-Benchmark.

Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation

Unsupervised domain adaptation (UDA) is vital for alleviating the workload of labeling 3D point cloud data and mitigating the absence of labels when facing a newly defined domain. Various methods of utilizing images to enhance the performance of cross-domain 3D segmentation have recently emerged. However, the pseudo labels, which are generated from models trained on the source domain and provide additional supervised signals for the unseen domain, are inadequate when utilized for 3D segmentation due to their inherent noisiness and consequently restrict the accuracy of neural networks. With the advent of 2D visual foundation models (VFMs) and their abundant knowledge prior, we propose a novel pipeline VFMSeg to further enhance the cross-modal unsupervised domain adaptation framework by leveraging these models. In this work, we study how to harness the knowledge priors learned by VFMs to produce more accurate labels for unlabeled target domains and improve overall performance. We first utilize a multi-modal VFM, which is pre-trained on large scale image-text pairs, to provide supervised labels (VFM-PL) for images and point clouds from the target domain. Then, another VFM trained on fine-grained 2D masks is adopted to guide the generation of semantically augmented images and point clouds to enhance the performance of neural networks, which mix the data from source and target domains like view frustums (FrustumMixing). Finally, we merge class-wise prediction across modalities to produce more accurate annotations for unlabeled target domains. Our method is evaluated on various autonomous driving datasets and the results demonstrate a significant improvement for 3D segmentation task.