72 accepted papers
In this work, we propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. Unlike training a variational autoencoder (VAE) from scratch, which primarily emphasizes low-level details, our approach leverages the rich semantic structure of found…
Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend is to adopt high-dimensional features from representation enc…
Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified frameworks, video generation and editing remain fragmented due…
Graph Out-of-Distribution (OOD) detection aims to identify whether a test graph deviates from the distribution of graphs observed during training, which is critical for ensuring the reliability of Graph Neural Networks (GNNs) when deployed in open-world scenarios. Recent advances in graph OOD detect
Flow-matching policies hold great promise for reinforcement learning (RL) by capturing complex, multi-modal action distributions. However, their practical application is often hindered by prohibitive inference latency and ineffective online exploration. Although recent works have employed one-step…
Recent unified models integrate understanding experts (e.g., LLMs) with generative experts (e.g., diffusion models), achieving strong multimodal performance. However, recent advanced methods such as BAGEL and LMFusion follow the Mixture-of-Transformers (MoT) paradigm, adopting a symmetric design tha
Graphs effectively model interactions in real-world applications such as social and trade networks, where Graph Neural Networks (GNNs) excel at tasks such as link prediction to enhance user experiences. Despite these benefits, users raise privacy concerns as user data can be exploited to improve GNN
We introduce MetricHMSR (Metric Human Mesh and Scene Recovery), a novel approach for metric human mesh and scene recovery from monocular images. Due to unrealistic assumptions in the camera model and inherent challenges in metric perception, existing approaches struggle to achieve human pose and met
Composition matters during the photo-taking process, yet many casual users struggle to frame well-composed images. To provide composition guidance, we introduce PhotoFramer, a multi-modal composition instruction framework. Given a poorly composed image, PhotoFramer first describes how to improve the
We introduce SOMA, the Spatial Memory framework for Out-of-Vision Manipulation in Vision-Language-Action (VLA) models. Most existing VLAs implicitly assume that task-relevant objects are always visible, leading to brittle and reactive behaviors when targets fall outside the camera’s field of view. S…
This paper presents a method for image relighting that enables precise and continuous control over multiple illumination attributes in a photograph. We formulate relighting as a conditional image generation task and introduce attribute tokens to encode distinct lighting factors such as intensity, co
Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision. Since these models typically rely on VLM backbones optimized for Visual Question Answering (VQA…
Existing feedforward image-to-3D methods mainly rely on 2D multi-view diffusion models that cannot guarantee 3D consistency. These methods easily collapse when changing the prompt view direction and mainly handle object-centric cases. In this paper, we propose a novel single-stage 3D diffusion model…
Recent advances in Large Language Models (LLMs) have raised urgent concerns about LLM-generated text authenticity, prompting regulatory demands for reliable identification mechanisms. Although watermarking offers a promising solution, existing approaches struggle to simultaneously achieve three cri…
This paper introduces Comprehensive Relighting, the first all-in-one approach that can both control and harmonize the lighting from an image or video of humans with arbitrary body parts from any scene. Building such a generalizable model is extremely challenging due to the lack of dataset, restricti…
Building on the success of diffusion models in image generation and editing, video editing has recently gained substantial attention. However, maintaining temporal consistency and motion alignment still remains challenging. To address these issues, this paper proposes DINO-guided Video Editing (DIVE…
Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For the existing methods, they focus on improving the diversity via pure exploration, mutual information optimization and learning temporal representation. Despite they perform wel…
Speech signals contain rich information, such as textual content, emotion, and speaker identity. To extract these features more efficiently, researchers are investigating joint training across multiple tasks, like Speech Emotion Recognition (SER) and Speaker Verification (SV), aiming to improve perf…
Accurately recognizing the structural regions of targeted objects is crucial for successful manipulation. In this study, we concentrate on the task of hanging crumpled garments on a rack, a common scenario in household environments. This context presents two primary challenges: (1) perceiving and gr
Existing human Motion Capture (MoCap) methods mostly focus on the visual similarity while neglecting the physical plausibility. As a result, downstream tasks such as driving virtual human in 3D scene or humanoid robots in real world suffer from issues such as timing drift and jitter, spatial problem…
We introduce the first generative model capable of simultaneous multi-object compositing, guided by both text and layout. Our model allows for the addition of multiple objects within a scene, capturing a range of interactions from simple positional relations (e.g., next to, in front of) to complex…
Existing feedforward subject-driven video customization methods mainly study single-subject scenarios due to the difficulty of constructing multi-subject training data pairs. Another challenging problem that how to use the signals such as depth, mask, camera, and text prompts to control and edit the…
Personalized image generation has emerged from the recent advancements in generative models. However, these generated personalized images often suffer from localized artifacts such as incorrect logos, reducing fidelity and fine-grained identity details of the generated results. Furthermore, there is…
We propose RelitLRM, a Large Reconstruction Model (LRM) for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations from sparse (4-8) posed images captured under unknown static lighting. Unlike prior inverse rendering methods requiring dense captures and sl…
This paper addresses the critical need for democratizing large language models (LLM) in the Arab world, a region that has seen slower progress in developing models comparable to state-of-the-art offerings like GPT-4 or GPT-3.5, due to a predominant focus on mainstream languages (e.g., English and Ch…
The latest advancement in large foundational model, SAM2, has demonstrated significant potential in 3D medical image segmentation due to their capability to effectively segment video streams. However, its application in medical image segmentation presents challenges, requiring extensive training on…
In multimodal emotion recognition, disentangled representation learning method effectively address the inherent heterogeneity among modalities. To facilitate the flexible integration of enhanced disentangled features into multimodal emotional features, we propose a task-driven multimodal emotion rec…
We present a lighting-aware image editing pipeline that, given a portrait image and a text prompt, performs single image relighting. Our model modifies the lighting and color of both the foreground and background to align with the provided text description. The unbounded nature in creativeness of a…
Text-to-video generative models have made significant strides, enabling diverse applications in entertainment, advertising, and education. However, generating RGBA video, which includes alpha channels for transparency, remains a challenge due to limited datasets and the difficulty of adapting existi…
We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while capturing visual variations. Inspired by recent video generation…
The seahorse's tail is renowned for its exceptional bending ability and strength owing to its unique biological structures. Inspired by this, this letter presents a novel modular cable-driven continuum robot with remarkable load capacity. By employing an asymmetric structure with both flexible and r
"Existing portrait relighting methods struggle with precise control over facial shadows, particularly when faced with challenges such as handling hard shadows from directional light sources or adjusting shadows while remaining in harmony with existing lighting conditions. In many situations, complet…
Graph neural networks (GNNs) have found widespread application in modeling graph data across diverse domains. While GNNs excel in scenarios where the testing data shares the distribution of their training counterparts (in distribution, ID), they often exhibit incorrect predictions when confronted wi…
At the core of portrait photography is the search for ideal lighting and viewpoint. The process often requires advanced knowledge in photography and an elaborate studio setup. In this work we propose Holo-Relighting a volumetric relighting method that is capable of synthesizing novel viewpoints and…
Generative object compositing emerges as a promising new avenue for compositional image editing. However the requirement of object identity preservation poses a significant challenge limiting practical usage of most existing methods. In response this paper introduces IMPRINT a novel diffusion-based…
In this study, we introduce a unified neural network architecture, the Deep Equilibrium Density Functional Theory Hamiltonian (DEQH) model, which incorporates Deep Equilibrium Models (DEQs) for predicting Density Functional Theory (DFT) Hamiltonians. The DEQH model inherently captures the self-consi…
Learning highly dynamic behaviors for robots has been a longstanding challenge. Traditional approaches have demonstrated robust locomotion, but the exhibited behaviors lack diversity and agility. They employ approximate models, which lead to compromises in performance. Data-driven approaches have be…
Foot contact is an important cue for human motion capture understanding and generation. Existing datasets tend to annotate dense foot contact using visual matching with thresholding or incorporating pressure signals. However these approaches either suffer from low accuracy or are only designed for s…
Portrait harmonization aims to composite a subject into a new background adjusting its lighting and color to ensure harmony with the background scene. Existing harmonization techniques often only focus on adjusting the global color and brightness of the foreground and ignore crucial illumination cue…
Predicting the mean-field Hamiltonian matrix in density functional theory is a fundamental formulation to leverage machine learning for solving molecular science problems. Yet, its applicability is limited by insufficient labeled data for training. In this work, we highlight that Hamiltonian predict…
With the popularity of large language models (LLMs) and their ability to handle longer input documents, there is a growing need for high-quality long document summarization datasets. Although many models already support 16k input, current lengths of summarization datasets are inadequate, and salient…
"Effective editing of personal content holds a pivotal role in enabling individuals to express their creativity, weaving captivating narratives within their visual stories, and elevate the overall quality and impact of their visual content. Therefore, in this work, we introduce , a novel framework t…
Denoising diffusion (score-based) generative models have become a popular choice for modeling complex data. Recently, a deep connection between forward-backward stochastic differential equations (SDEs) and diffusion-based models has been established, leading to the development of new SDE variants su…
While graph neural networks (GNNs) dominate the state-of-the-art for exploring graphs in real-world applications, they have been shown to be vulnerable to a growing number of privacy attacks. For instance, link stealing is a well-known membership inference attack (MIA) on edges that infers the prese…
Real-world graphs generally have only one kind of tendency in their connections. These connections are either homophilic-prone or heterophily-prone. While graphs with homophily-prone edges tend to connect nodes with the same class (i.e., intra-class nodes), heterophily-prone edges tend to build rela…
Current image harmonization methods consider the entire background as the guidance for harmonization. However, this may limit the capability for user to choose any specific object/person in the background to guide the harmonization. To enable flexible interaction between user and harmonization, we i…
Recent portrait relighting methods have achieved realistic results of portrait lighting effects given a desired lighting representation such as an environment map. However, these methods are not intuitive for user interaction and lack precise lighting control. We introduce LightPainter, a scribble-b…
In an era where images and visual content dominate our digital landscape, the ability to manipulate and personalize these images has become a necessity. Envision seamlessly substituting a tabby cat lounging on a sunlit window sill in a photograph with your own playful puppy, all while preserving the…
Recent advancements in deep generative models have facilitated the creation of photo-realistic images across various tasks. However, these generated images often exhibit perceptual artifacts in specific regions, necessitating manual correction. In this study, we present a comprehensive empirical exa…
Lighting effects such as shadows or reflections are key in making synthetic images realistic and visually appealing. To generate such effects, traditional computer graphics uses a physically-based renderer along with 3D geometry. To compensate for the lack of geometry in 2D Image compositing, recent…
The distillation of ranking models has become an important topic in both academia and industry. In recent years, several advanced methods have been proposed to tackle this problem, often leveraging ranking information from teacher rankers that is absent in traditional classification settings. To dat…
Learning-based image harmonization techniques are usually trained to undo synthetic global transformations, applied to a masked foreground in a single ground truth photo. This simulated data does not model many important appearance mismatches (illumination, object boundaries, etc.) between foregroun…
Knowledge graph completion (KGC) predicts missing links and is crucial for real-life knowledge graphs, which widely suffer from incompleteness. KGC methods assume a knowledge graph is static, but that may lead to inaccurate prediction results because many facts in the knowledge graphs change over…
Deep image matting methods have achieved increasingly better results on benchmarks (e.g., Composition-1k/alphamatting.com). However, the robustness, including robustness to trimaps and generalization to images from different domains, is still under-explored. Although some works propose to either ref…
"Shadows are essential for realistic image compositing. Physics based shadow rendering methods require 3D geometries, which are not always available. Deep learning-based shadow synthesis methods learn a mapping from the light information to an object’s shadow without explicitly modeling the shadow g…
We introduce DoubleField, a novel framework combining the merits of both surface field and radiance field for high-fidelity human reconstruction and rendering. Within DoubleField, the surface field and radiance field are associated together by a shared feature embedding and a surface-guided sampling…
Abstractive summarization has made tremendous progress in recent years. In this work, we perform fine-grained human annotations to evaluate long document abstractive summarization systems (i.e., models and metrics) with the aim of implementing them to generate reliable summaries. For long document a…
Despite the impressive representation capacity of vision transformer models, current light-weight vision transformer models still suffer from inconsistent and incorrect dense predictions at local regions. We suspect that the power of their self-attention mechanism is limited in shallower and thinner…
Visualization of the surgical needle is critical for an image guided insertion. However, it is difficult to obtain a 3D tip pose of a steerable flexible needle under 2D US images. In this letter, an image processing method is used to extract the needle shaft radial cross-sectional centroid coordinat
Group equivariance (e.g. SE(3) equivariance) is a critical physical symmetry in science, from classical and quantum physics to computational biology. It enables robust and accurate prediction under arbitrary reference transformations. In light of this, great efforts have been put on encoding this sy…
This article proposed a humanoid obstacle passability strategy (OPS) to enhance human-exoskeleton integrated system to cross over multi-obstacle in sagittal plane. A hybrid bounding box integrated with closeness regression in L-shape section and synchronous convergence in convex hull search (HBB-LC)
This paper presents a hand-worn assistive device to assist a visually impaired person with object manipulation. The device uses a Google Pixel 3 as the computational platform, a Structure Core (SC) sensor for perception, a speech interface, and a haptic interface for human-device interaction. W-ROMA…
Proteins are the main machinery of life and protein functions are largely determined by their 3D structures. The measurement of the pairwise proximity between amino acids of a protein, known as inter-residue contact map, well characterizes the structural information of a protein. Protein contact pre…
We propose Mask Guided (MG) Matting, a robust matting framework that takes a general coarse mask as guidance. MG Matting leverages a network (PRN) design which encourages the matting model to provide self-guidance to progressively refine the uncertain regions through the decoding process. A series o…
Speech emotion recognition is a challenging task due to the ambiguity of emotion, which makes it difficult to learn the features of emotion data using machine learning algorithms. However, previous studies conventionally ignore the ambiguity of emotion and treat the emotion data as the same difficul…
Image harmonization aims to improve the quality of image compositing by matching the "appearance"" (e.g., color tone, brightness and contrast) between foreground and background images. However, collecting large-scale annotated datasets for this task requires complex professional retouching. Instead,…
In this paper, we propose a new scheme based on the Sampson distance (SD) to describe visual feature residuals for visual-inertial odometry (VIO). Unlike the epipolar-constraint-based SD for visual odometry (VO), the proposed SD is formulated based on the perspective projection constraint. We proved…
This paper presents a visual positioning system (VPS) for real-time pose estimation of a robotic navigation aid (RNA) for assistive navigation. The core of the VPS is a new method called depth-enhanced visual-inertial odometry (DVIO) that uses an RGB-D camera and an inertial measurement unit (IMU) t…
This paper presents a new visual-inertial odometry, term DUI-VIO, for estimating the motion state of an RGB-D camera. First, a Gaussian mixture model (GMM) to is employed to model the uncertainty of the depth data for each pixel on the camera's color image. Second, the uncertainties are incorporated
This paper presents VCU-RVI, a new visual inertial odometry (VIO) benchmark with a set of diverse data sequences in different indoor scenarios. The benchmark was captured using an Structure Core (SC) sensor, consisting of an RGB-D camera and an IMU. It provides aligned color and depth images with 64…
We propose a new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazing all together. The end-to-end learning is achieved by directly embedding the atmospheric scattering model i…
Single image rain streak removal is an extremely challenging problem due to the presence of non-uniform rain densities in images. We present a novel density-aware multi-stream densely connected convolutional neural network-based algorithm, called DID-MDN, for joint rain density estimation and de-rai…